© 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. 9-GEMMASCOPE-RES-131K
    11. 5408
    Prev
    Next
    INDEX
    Explanations

    mentions of sudden events, particularly related to health or critical situations

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

    sudden event or change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.73
     loaf
    -0.59
    RegressionTest
    -0.58
     estekak
    -0.58
     AspNetCore
    -0.55
    hyrchwyd
    -0.55
    NameInMap
    -0.53
     Wikimedijinoj
    -0.53
     invokingState
    -0.52
     Vay
    -0.52
    POSITIVE LOGITS
     sudden
    1.91
    Sudden
    1.67
     Sudden
    1.56
    sud
    1.09
     abrupt
    0.97
     unexpected
    0.93
    unexpected
    0.83
     rapid
    0.82
     suddenly
    0.78
    Unexpected
    0.77
    Activations Density 0.004%

    No Known Activations