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. 62187
    Prev
    Next
    INDEX
    Explanations

    instances of negation or disagreement

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

    Empty line breaks that separate paragraphs or content sections in various document formats, often appearing between distinct blocks of text or HTML elements.

    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
    IndentedString
    -0.32
    adə
    -0.31
    dataclass
    -0.29
    ValueStyle
    -0.29
     مشين
    -0.28
     Roskov
    -0.27
    IsContent
    -0.26
     officially
    -0.25
    ۣ
    -0.24
     ordeal
    -0.24
    POSITIVE LOGITS
    rungsseite
    0.67
     kasarigan
    0.66
     ſen
    0.64
     ſta
    0.63
     فريبيس
    0.60
     disambiguazione
    0.60
     Ejecutivo
    0.58
     beſ
    0.58
     ſever
    0.58
     propOrder
    0.57
    Activations Density 0.090%

    No Known Activations