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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105964
    Prev
    Next
    INDEX
    Explanations

    instances of ellipsis or pauses in text

    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
     AssemblyVersion
    -0.93
    AndEndTag
    -0.81
    aarrggbb
    -0.75
    addCriterion
    -0.73
    AsUp
    -0.72
    +#+#
    -0.66
    AntiForgeryToken
    -0.64
    WebElementEntity
    -0.64
    ArrowToggle
    -0.63
     doInBackground
    -0.63
    POSITIVE LOGITS
     vors
    0.28
    laki
    0.27
     velkommen
    0.26
    import
    0.25
     oiseaux
    0.25
     professeurs
    0.25
    GCT
    0.24
     dvs
    0.24
     presenta
    0.24
    Рас
    0.24
    Activations Density 0.008%

    No Known Activations