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. 122819
    Prev
    Next
    INDEX
    Explanations

    legal terminology and conditions related to court proceedings

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

    Technical terms, common nouns, and grammatical connectors that appear in structured text formats like legal documents, code, or scientific writing.

    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
    hörige
    -0.31
     prêtres
    -0.31
     commercial
    -0.30
    ACIÓN
    -0.28
     quartiers
    -0.28
    underbrace
    -0.28
    Año
    -0.28
     Holanda
    -0.28
    ACION
    -0.27
     détail
    -0.27
    POSITIVE LOGITS
    SourceChecksum
    0.89
    DockStyle
    0.76
    awtextra
    0.71
    BufferException
    0.67
     GenerationType
    0.67
    StructEnd
    0.65
     للاسماء
    0.64
    setVerticalGroup
    0.63
    IsMutable
    0.63
    ngdoc
    0.62
    Activations Density 0.394%

    No Known Activations