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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130930
    Prev
    Next
    INDEX
    Explanations

    elements related to legal counsel and proceedings

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

    Verbs and terms related to handling issues, questions, or content in legal and technical documents, often appearing in procedural contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     חיצוניים
    -0.65
    Спасылкі
    -0.64
    colgroup
    -0.57
     ſch
    -0.56
    jsxFileName
    -0.56
    DockStyle
    -0.55
    ArrowToggle
    -0.52
     ſche
    -0.50
    MethodManager
    -0.49
     informée
    -0.49
    POSITIVE LOGITS
     propOrder
    0.36
     contenidos
    0.35
     topics
    0.35
     contenuto
    0.35
     Express
    0.35
    retudo
    0.33
     contenus
    0.33
     obsah
    0.33
    Express
    0.33
    Kenmerken
    0.32
    Activations Density 0.210%

    No Known Activations