© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13203
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and mathematical concepts

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

    before citations or series names

    np_acts-logits-general · gemini-2.0-flash

    academic series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Билгалдахарш
    -0.53
    SharedCtor
    -0.52
    rawDesc
    -0.50
    Hentet
    -0.50
    aarrggbb
    -0.49
    Tikang
    -0.48
    osocial
    -0.46
    GTCX
    -0.44
    KommentareTeilen
    -0.44
     strijd
    -0.43
    POSITIVE LOGITS
     series
    0.84
     Series
    0.76
    Series
    0.69
    series
    0.66
    シリーズ
    0.62
    系列
    0.58
     SERIES
    0.58
     Série
    0.54
     serie
    0.54
    reihe
    0.53
    Activations Density 0.177%

    No Known Activations