NCP-GENL LLM Architecture Practice Question
In the context of the Transformer architecture, what is the primary function of the Feed-Forward Network (FFN) layers applied after the attention mechanism?
⚠ Common exam trap
Candidates often confuse the FFN's role with the attention mechanism's role. They incorrectly attribute the 'capturing of relationships between tokens' to the FFN, rather than the attention mechanism.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
To process the hidden state representations with non-linear activations.
The FFN layers provide non-linear transformations that allow the model to process information extracted by the attention mechanism. While attention focuses on relationships between tokens, the FFN applies point-wise non-linearities to project these features into higher-dimensional spaces. This is essential for learning complex representations and mappings that ultimately drive the model's predictive accuracy and reasoning capabilities across diverse input patterns.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
To calculate the attention scores between different tokens in the sequence.
Why it's wrong here
Attention scores are computed within the multi-head attention blocks, not the feed-forward network. The attention mechanism uses dot products of query and key vectors to determine relevance, whereas the FFN is a separate module focused on feature transformation and non-linear processing of the resulting hidden states.
- ✓
To process the hidden state representations with non-linear activations.
Why this is correct
The FFN typically consists of two linear transformations with a non-linear activation function, like SwiGLU or ReLU, in between. This structure enables the model to learn complex mappings of input features, significantly increasing its capacity to understand nuances that linear attention projections alone might fail to capture effectively.
- ✗
To manage the memory allocation for the KV cache during multi-token generation.
Why it's wrong here
Memory management is a system-level function performed by the inference engine (e.g., vLLM or TensorRT-LLM), not by the neural network's architecture layers. The FFN is a static part of the model weights and does not interact with the dynamic memory allocation strategies used for the KV cache.
- ✗
To reduce the sequence length of the input tokens to a fixed size.
Why it's wrong here
The FFN operates on each token independently and does not modify the sequence length. Sequence length reduction would require pooling layers or strided attention, which are not part of the standard FFN block. The FFN maintains the dimensionality and sequence length of its input throughout its transformation.
About these practice questions
One of 352 original NCP-GENL practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official NVIDIA exam blueprint
This NCP-GENL practice question is part of Courseiva's free NVIDIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the NCP-GENL exam.