© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10330
    Prev
    Next
    INDEX
    Explanations

    references to the "Stand Your Ground" law and self-defense, specifically in the context of the Martin/Zimmerman case.

    oai_token-act-pair · gemini-2.0-flash

    legal use of force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.65
    ImageContext
    -0.60
     anahtar
    -0.59
    forChild
    -0.54
    ArgsConstructor
    -0.52
     infallib
    -0.52
    PreferredItem
    -0.48
    idł
    -0.47
    inheit
    -0.46
     spéciales
    -0.46
    POSITIVE LOGITS
    DotNetBar
    0.71
    SBATCH
    0.58
    gonic
    0.57
    detectChanges
    0.57
    #
    0.57
    فایل‌لار
    0.56
     الرخصة
    0.55
     demografica
    0.52
    djangoproject
    0.52
     StatefulWidget
    0.50
    Activations Density 1.659%

    No Known Activations