© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104773
    Prev
    Next
    INDEX
    Explanations

    numerical data and citation formats

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    argout
    -0.33
    URS
    -0.32
    urs
    -0.31
     Fur
    -0.31
    Brainz
    -0.31
    .”
    -0.31
    subpackage
    -0.31
     TMPro
    -0.30
     delar
    -0.30
    UnitId
    -0.30
    POSITIVE LOGITS
     plufieurs
    0.67
    存于互联网档案馆
    0.65
    lunda
    0.60
    AndEndTag
    0.59
     שוליים
    0.59
    parsedMessage
    0.58
    tagHelperRunner
    0.57
    SharedCtor
    0.57
    ########.
    0.56
    GEBURTSDATUM
    0.56
    Activations Density 0.010%

    No Known Activations