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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102251
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to programming constructs, specifically parentheses and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.84
     مشين
    -0.74
    GEBURTSDATUM
    -0.69
    astéroïdes
    -0.67
    expandindo
    -0.67
    extAlignment
    -0.62
    ItemBackground
    -0.59
    reportWebVitals
    -0.59
    brido
    -0.57
    Personensuche
    -0.56
    POSITIVE LOGITS
    出版年
    0.50
    CGContext
    0.30
     Ale
    0.29
     hers
    0.28
    hoto
    0.27
    المكان
    0.27
     Mint
    0.27
     Mai
    0.27
     Sang
    0.27
    ungs
    0.27
    Activations Density 0.016%

    No Known Activations