© 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. 3891
    Prev
    Next
    INDEX
    Explanations

    references to environmental context and conditions

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

    recent years

    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
     American
    -0.55
    American
    -0.52
     badass
    -0.51
    Miami
    -0.49
     #
    -0.49
     signature
    -0.48
     Miami
    -0.46
     pop
    -0.46
     superpowers
    -0.45
     createContext
    -0.45
    POSITIVE LOGITS
     larmes
    0.73
     auffi
    0.73
     difficultés
    0.71
     locaux
    0.71
     ")");
    0.69
    AxisAlignment
    0.69
     feroit
    0.68
     dieß
    0.68
    )");
    0.68
     réfugiés
    0.68
    Activations Density 0.002%

    No Known Activations