© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 91220
    Prev
    Next
    INDEX
    Explanations

    structures and syntax related to programming code

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

    0 followed by parser or Z

    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
     Überras
    -0.32
     débats
    -0.32
     Histórico
    -0.32
     Ahnung
    -0.31
     GoogleFonts
    -0.30
     Moreno
    -0.30
     encima
    -0.29
     TextAppearance
    -0.29
     setShow
    -0.29
     Beobachtung
    -0.28
    POSITIVE LOGITS
    render
    1.23
     render
    1.18
     Render
    1.02
    Render
    0.91
     rendered
    0.89
     renders
    0.89
     Rendering
    0.84
     rendering
    0.81
     rend
    0.71
     rende
    0.68
    Activations Density 0.001%

    No Known Activations