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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 25699
    Prev
    Next
    INDEX
    Explanations

    specific technical specifications, guidelines, and requirements related to products or machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    postcss
    -0.35
    ParseTree
    -0.34
     reflecting
    -0.33
    反映
    -0.33
     solides
    -0.31
    Vegeu
    -0.30
     reflexión
    -0.30
    曖昧さ回避
    -0.30
    自作
    -0.30
     fotografía
    -0.30
    POSITIVE LOGITS
     AssemblyCulture
    0.67
     NSCoder
    0.65
    ruik
    0.56
    tanleria
    0.52
    Kanpo
    0.52
    Atoi
    0.50
    arangay
    0.49
     warnings
    0.48
    WebVitals
    0.48
     ModelExpression
    0.47
    Activations Density 0.013%

    No Known Activations