© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 81250
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, particularly function definitions and parameters

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    input data types

    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
    Negative Logits
    AccessorTable
    -0.47
    NamedQuery
    -0.42
    adav
    -0.40
    shafen
    -0.40
    MarshalTo
    -0.39
    Citiți
    -0.39
    stdc
    -0.39
    StreamWriter
    -0.38
     stable
    -0.38
    principalTable
    -0.38
    POSITIVE LOGITS
     input
    0.73
    input
    0.66
     Input
    0.59
    Input
    0.59
     INPUT
    0.53
    ORIGINAL
    0.52
     оригинал
    0.52
     inputs
    0.50
    输入
    0.50
    original
    0.49
    Activations Density 0.038%

    No Known Activations