© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3586
    Prev
    Next
    INDEX
    Explanations

    function definitions and control flow statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     zurück
    -0.39
     órgãos
    -0.39
    เตอร์
    -0.36
    othek
    -0.36
     avez
    -0.34
     teritor
    -0.33
    vő
    -0.33
     dissolves
    -0.33
    memcpy
    -0.33
    coles
    -0.32
    POSITIVE LOGITS
    SerializedSize
    1.14
     continúas
    1.10
     autorytatywna
    1.05
    GEBURTSDATUM
    1.02
     виправивши
    1.02
     resourceCulture
    1.01
     kasarigan
    0.96
     disambiguazione
    0.93
    Билгалдахарш
    0.92
    رشف
    0.92
    Activations Density 0.011%

    No Known Activations