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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103139
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court cases and judicial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.42
    adaptiveStyles
    -0.37
    Besch
    -0.37
     المس
    -0.36
     Thorpe
    -0.36
     Doing
    -0.35
     Bad
    -0.34
     ά
    -0.34
     Besch
    -0.34
     trail
    -0.33
    POSITIVE LOGITS
    ьаж
    0.68
    تقاوى
    0.65
     Vikipedi
    0.62
     EconPapers
    0.61
     estekak
    0.59
     ویکی‌پدیای
    0.56
     дописавши
    0.54
     препратки
    0.54
     BoxFit
    0.53
     ویکی‌پدیا
    0.53
    Activations Density 0.060%

    No Known Activations