124095 Page

In the context of machine learning and neural networks, identifies a specific "feature" or SAE (Sparse Autoencoder) latent within the Gemma 2 9b (IT) model, specifically in the 20-GEMMASCOPE-RES-131K layer. Feature 124095: Negative Logits

This feature is a computational "neuron" that activates in response to specific linguistic patterns. According to Neuronpedia , its primary function is associated with for specific characters or tokens. 124095

: It suppresses or identifies specific output tokens, acting as a filter within the model's decision-making process. In the context of machine learning and neural

: It is often analyzed alongside other similar features within the Gemma Scope to understand how the model represents complex concepts or steers its own internal logic. Other Technical References : It suppresses or identifies specific output tokens,

: The number also appears in hardware benchmarks, such as a Generic SSD performance test recorded on June 29, 2025, for a Raspberry Pi 5B Go to product viewer dialog for this item. .