© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102753
    Prev
    Next
    INDEX
    Explanations

    datetime values and formats

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.68
     للاسماء
    -0.67
     NSCoder
    -0.66
     الحره
    -0.65
    ValueStyle
    -0.64
    setVerticalGroup
    -0.61
    :"-"`
    -0.60
    #![
    -0.58
    OGND
    -0.57
     ostavi
    -0.57
    POSITIVE LOGITS
    듈
    0.42
    líben
    0.38
    Sommaire
    0.35
     gustado
    0.34
    power
    0.34
    currentItem
    0.34
     Gin
    0.34
    ConfigureAwait
    0.33
    我说
    0.33
    Einzelnachweise
    0.33
    Activations Density 0.019%

    No Known Activations