© 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. 24562
    Prev
    Next
    INDEX
    Explanations

    tokens related to specific functions and methods in programming or API documentation

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

    code and mathematical symbols

    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
     pinulongan
    -0.54
    Preparazione
    -0.52
    )"),
    -0.47
    SqlClient
    -0.46
     TextAppearance
    -0.44
    省市镇
    -0.44
    ]:
    -0.43
    rawDesc
    -0.43
    ductory
    -0.43
    tvguidetime
    -0.42
    POSITIVE LOGITS
    //*
    0.75
    :*
    0.75
     *
    0.74
    .*
    0.73
     (*
    0.73
    !*
    0.71
    #*
    0.70
    ?*
    0.69
    ********
    0.68
    %*
    0.68
    Activations Density 0.679%

    No Known Activations