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. 105110
    Prev
    Next
    INDEX
    Explanations

    queries related to programming, coding issues, and requests for feedback or assistance

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

    Text containing references to questions, problems, or requests for help, particularly in technical contexts like code reviews, forum discussions, or advice settings.

    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
     plazos
    -0.35
     propiedades
    -0.31
    대로
    -0.30
     estadísticas
    -0.30
     responsabilidad
    -0.30
    บอล
    -0.29
     dimensiones
    -0.29
     publicidad
    -0.29
    essentiel
    -0.29
     devrez
    -0.28
    POSITIVE LOGITS
     للاسماء
    0.78
     وتسجيلات
    0.76
    GEBURTS
    0.72
    Personendaten
    0.66
     invokingState
    0.66
    verifyException
    0.65
     nakalista
    0.63
     pinulongan
    0.62
    ніципалі
    0.62
    EndProject
    0.61
    Activations Density 0.075%

    No Known Activations