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. 130964
    Prev
    Next
    INDEX
    Explanations

    phrases involving specific quantities and measurements related to results or conditions

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

    Functional words, prepositions, and connecting elements that establish relationships between parts of a sentence, particularly in technical or formal writing contexts.

    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
    NameInMap
    -0.68
    Tikang
    -0.57
    RectangleBorder
    -0.55
    Rujuakan
    -0.51
    utives
    -0.50
     BoxFit
    -0.50
    AsUp
    -0.49
    HtmlAttribute
    -0.48
    AnchorStyles
    -0.47
    InjectAttribute
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.45
     esquecer
    0.41
     Aérea
    0.38
     äldre
    0.37
    cení
    0.34
     liksom
    0.34
     Wolken
    0.34
    bardziej
    0.34
    zetten
    0.34
     nonUne
    0.34
    Activations Density 0.216%

    No Known Activations