© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37924
    Prev
    Next
    INDEX
    Explanations

    references to layers and films in a semiconductor context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    layer on top

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.60
    
    -0.46
     Sous
    -0.43
     Scalars
    -0.43
     predeceased
    -0.42
    Під
    -0.40
    AISSEE
    -0.40
     <=",
    -0.40
    携
    -0.39
    ActionCreators
    -0.39
    POSITIVE LOGITS
     encima
    1.30
     atop
    1.27
     sobre
    1.05
     diatas
    1.04
     above
    1.02
     overlying
    1.02
     върху
    0.98
     dessus
    0.97
     over
    0.97
     над
    0.96
    Activations Density 0.179%

    No Known Activations