© 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. 20-GEMMASCOPE-RES-131K
    11. 42657
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural markers in the text

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

    XML comments and code tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Negative Logits
    setVerticalGroup
    -0.32
    SharedDtor
    -0.30
     recentemente
    -0.28
     funcionarios
    -0.26
    arikat
    -0.26
     infine
    -0.25
     secrétaire
    -0.25
     enfin
    -0.25
     ofici
    -0.24
     lainnya
    -0.24
    POSITIVE LOGITS
    __(/*!
    0.75
    matchCondition
    0.75
     للمعارف
    0.71
     насељу
    0.68
     otomatig
    0.68
     мәкал
    0.67
    __*/
    0.67
    RTLR
    0.66
     كومونز
    0.66
    ⟬
    0.65
    Activations Density 0.042%

    No Known Activations