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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91250
    Prev
    Next
    INDEX
    Explanations

    news reports and mentions of public figures

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

    reported actions and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obviously
    -0.66
    obviously
    -0.54
     ovviamente
    -0.53
     Obviously
    -0.52
     clearly
    -0.51
     évidemment
    -0.50
     obviamente
    -0.50
    Obviously
    -0.50
     chiaramente
    -0.49
     jelas
    -0.49
    POSITIVE LOGITS
     secretly
    0.66
     secret
    0.61
     jopa
    0.61
    有意
    0.61
     bribe
    0.59
     яко
    0.58
     planning
    0.56
     planned
    0.55
     plans
    0.54
    Possible
    0.52
    Activations Density 0.065%

    No Known Activations