© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 105609
    Prev
    Next
    INDEX
    Explanations

    references to official roles and positions, particularly in a corporate or governmental context

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

    Function words or connective elements that link related parts of compound terms, especially in technical contexts like code, references, citations, or digital content.

    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
     يتيمه
    -0.54
     للمعارف
    -0.48
     cherchés
    -0.44
     مرئيه
    -0.42
    horesis
    -0.40
    Дереккөздер
    -0.40
     Mercure
    -0.36
    ynx
    -0.36
    astify
    -0.35
     carport
    -0.35
    POSITIVE LOGITS
     AspNetCore
    0.54
     AssemblyCompany
    0.52
    DockStyle
    0.48
     AssemblyCulture
    0.46
    PDOException
    0.43
     balance
    0.42
     незавершена
    0.41
    TypedDataSet
    0.41
    XmlRootElement
    0.41
     Obrador
    0.41
    Activations Density 0.093%

    No Known Activations