© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3804
    Prev
    Next
    INDEX
    Explanations

    phrases related to killing or violence

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

    Sentences about killing or being killed

    np_acts-logits-general · gemini-2.0-flash

    kill or kill off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.54
    nextProps
    -0.52
     estekak
    -0.48
    UnusedPrivate
    -0.48
    enteuer
    -0.48
     nakalista
    -0.47
     Independ
    -0.47
    depar
    -0.46
    weiten
    -0.45
    ajs
    -0.45
    POSITIVE LOGITS
     kill
    0.97
     Kill
    0.83
     KILL
    0.78
     kills
    0.77
     killing
    0.77
    Kill
    0.75
     Killing
    0.75
    Killing
    0.71
    kill
    0.70
     killed
    0.68
    Activations Density 0.174%

    No Known Activations