© 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. 17106
    Prev
    Next
    INDEX
    Explanations

    conventions and rules related to variable naming in programming

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

    dollar and underscore 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
    Negative Logits
     saksi
    -0.44
     Stimmen
    -0.40
     Preguntas
    -0.39
     Dimensiones
    -0.38
    Autriche
    -0.37
     mitte
    -0.36
     vaksinasi
    -0.36
     ModelExpression
    -0.36
     calorías
    -0.35
    occa
    -0.35
    POSITIVE LOGITS
     symbol
    0.73
     symbols
    0.69
     character
    0.68
     characters
    0.62
     símbolo
    0.60
    ymbol
    0.59
    symbols
    0.59
     Symbols
    0.58
    Symbol
    0.57
     Symbol
    0.57
    Activations Density 0.156%

    No Known Activations