© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 97933
    Prev
    Next
    INDEX
    Explanations

    actions and commands related to system operations or user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interface action commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    HostException
    -0.51
     superare
    -0.34
     appréci
    -0.34
     FileNotFound
    -0.34
    DoubleQuotes
    -0.33
     TestBed
    -0.33
     BufferedWriter
    -0.33
     perished
    -0.33
     Spisak
    -0.32
     Masuk
    -0.32
    POSITIVE LOGITS
     actions
    1.02
     action
    0.98
     Actions
    0.97
    Actions
    0.91
     acción
    0.89
    actions
    0.87
    Action
    0.87
     ACTIONS
    0.86
    action
    0.86
    getAction
    0.85
    Activations Density 0.043%

    No Known Activations