Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1220
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to lawsuits and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.85
    Билгалдахарш
    -0.77
    tagHelperRunner
    -0.71
    ContentAsync
    -0.70
    MemoryWarning
    -0.65
    esehen
    -0.64
    withIdentifier
    -0.64
    הערות
    -0.63
     FontWeight
    -0.61
     }{@
    -0.59
    POSITIVE LOGITS
     lawsuits
    1.15
     lawsuit
    1.13
     litigation
    1.05
     suing
    0.98
     sued
    0.90
     suit
    0.84
     litig
    0.82
     plaintiffs
    0.82
     Litigation
    0.79
     alleging
    0.75
    Activations Density 1.041%

    No Known Activations