© 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. 40847
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal processes and warrants for arrest

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

    arrest warrant

    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
     selam
    -0.34
     onts
    -0.34
     المس
    -0.32
    épreuve
    -0.32
    endmodule
    -0.32
     ogen
    -0.32
    InputModule
    -0.32
    XmlAccessorType
    -0.32
    hama
    -0.31
     pageSize
    -0.30
    POSITIVE LOGITS
     warrant
    0.89
     warrants
    0.84
     court
    0.71
     Warrant
    0.65
     judicial
    0.64
     judgment
    0.64
     WARRANT
    0.63
    Court
    0.62
    Judge
    0.62
     judgement
    0.61
    Activations Density 0.114%

    No Known Activations