© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and their associated properties in a structured data format

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

    MRI;

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    Demografie
    -0.50
    olingo
    -0.46
     Bile
    -0.45
    ürzen
    -0.45
    بوابة
    -0.44
    Postup
    -0.43
     Licht
    -0.43
     препратки
    -0.43
     Obec
    -0.43
    entic
    -0.43
    POSITIVE LOGITS
    aarrggbb
    0.66
    AndEndTag
    0.59
    writeFieldEnd
    0.58
    mazoo
    0.56
    ThroughAttribute
    0.55
     intStringLen
    0.55
     للاسماء
    0.55
    पया
    0.54
     الحره
    0.53
    errHandler
    0.52
    Activations Density 0.007%

    No Known Activations