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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1530
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantifiable data within the text

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

    specific numerical and date-related information.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    numerical values related to currency, pricing, and financial information.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mentions of explicit quantitative info—dates/times, numbers, prices, measurements, and technical specifications, often with symbols, units, or hyphenated formats.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    punctuation marks and special characters, particularly periods, commas, parentheses, and quotation marks that appear in formal or technical text contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MethodImpl
    -0.40
    ždý
    -0.40
    الحياه
    -0.39
     gué
    -0.38
     faune
    -0.37
    INCREF
    -0.37
     NDEBUG
    -0.37
     Barnard
    -0.36
    Forge
    -0.36
     marbre
    -0.36
    POSITIVE LOGITS
     surla
    0.93
    ValueStyle
    0.80
    sizeCache
    0.59
     CreateTagHelper
    0.57
     disambiguazione
    0.56
     Photocase
    0.56
    ItemBackground
    0.55
     كومونز
    0.54
    ArgsConstructor
    0.52
    ViewImports
    0.50
    Activations Density 0.068%

    No Known Activations