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. 130916
    Prev
    Next
    INDEX
    Explanations

    complex scientific or technical terms and their contextual usage

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

    Technical terms and notation appearing in academic, scientific, and legal documents, often representing specific parameters, chemical compounds, mathematical symbols, or specialized vocabulary within their respective domains.

    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
    RenderAtEndOf
    -0.59
    rungsseite
    -0.47
    setVerticalGroup
    -0.45
    دانشنامهٔ
    -0.45
     שוליים
    -0.41
    WebVitals
    -0.40
     defaultstate
    -0.40
     surla
    -0.40
    Distribuzione
    -0.37
     للاسماء
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.49
     arşivlendi
    0.45
    getRuntime
    0.42
    +#+
    0.42
    亲
    0.40
    evos
    0.40
    ColElement
    0.39
     [][]
    0.39
    iexcl
    0.38
    OGND
    0.38
    Activations Density 0.023%

    No Known Activations