© 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. 121380
    Prev
    Next
    INDEX
    Explanations

    contexts related to critical or precarious situations

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

    into crisis or peril

    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
    metz
    -0.44
     tunt
    -0.39
    bleau
    -0.38
    hner
    -0.38
    Male
    -0.38
    BeforeMethod
    -0.37
    vinner
    -0.37
     ráp
    -0.37
     popr
    -0.37
    akas
    -0.37
    POSITIVE LOGITS
    陷入
    0.60
     crisis
    0.52
     autorytatywna
    0.48
    úgó
    0.47
    esez
    0.46
     CRISIS
    0.44
     peril
    0.44
     plunged
    0.44
    TypedDataSet
    0.43
     recovery
    0.43
    Activations Density 0.206%

    No Known Activations