© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9918
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement officers and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schmel
    -0.70
    NewGuid
    -0.70
    <()>
    -0.69
    anical
    -0.69
    NOPQRST
    -0.68
    EndInit
    -0.66
    haway
    -0.66
     Bode
    -0.63
    PathVariable
    -0.63
    RequestParam
    -0.63
    POSITIVE LOGITS
     officers
    2.90
     Officers
    2.68
     officer
    2.66
    Officers
    2.61
     OFFICER
    2.53
     Officer
    2.52
    officers
    2.50
     OFFICERS
    2.49
    officer
    2.46
    Officer
    2.33
    Activations Density 0.048%

    No Known Activations