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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-131K
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    instances of the word "kill" and its variations associated with various contexts

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

    kill, kill rate, kill switches

    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
    ように
    -0.46
     Mateo
    -0.45
    vierno
    -0.44
    toHaveBeen
    -0.44
    workspace
    -0.42
     történ
    -0.41
     CSP
    -0.41
     Farina
    -0.41
    UserContext
    -0.41
    icordia
    -0.40
    POSITIVE LOGITS
     kill
    0.97
     Kill
    0.93
    Kill
    0.91
     KILL
    0.83
    kill
    0.82
     kills
    0.81
    KILL
    0.79
     Killing
    0.72
     killed
    0.71
     killing
    0.70
    Activations Density 0.017%

    No Known Activations