© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5638
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases relating to court cases and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.85
     BeautifulSoup
    -0.75
    Билгалдахарш
    -0.73
     énergé
    -0.71
     }{@
    -0.71
    KommentareTeilen
    -0.70
     onOptions
    -0.70
     مشين
    -0.67
    ыгана
    -0.67
    withIdentifier
    -0.67
    POSITIVE LOGITS
     lawsuit
    0.94
     suing
    0.92
     lawsuits
    0.92
     litigation
    0.87
     sued
    0.83
     alleging
    0.71
     plaintiffs
    0.70
     damages
    0.70
     Litigation
    0.66
     litig
    0.63
    Activations Density 1.084%

    No Known Activations