© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistical data within the text

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

    programming and technical documentation metadata, such as comments, version numbers, and code-related information.

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

    decimal numbers written with a period (floating-point numeric values).

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

    whitespace or indentation at the beginning of lines, particularly in structured text like code, XML, or formatted documents.

    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
     ainfi
    -0.56
    tvguidetime
    -0.56
     plufieurs
    -0.54
     disfrute
    -0.52
     voordelen
    -0.52
     månader
    -0.50
     investissements
    -0.50
     navideño
    -0.50
     navideños
    -0.50
    ydı
    -0.48
    POSITIVE LOGITS
    __(/*!
    0.83
     ③
    0.62
    enumi
    0.62
    󠁿
    0.58
    seteq
    0.58
     AssemblyCompany
    0.55
    \{\\
    0.54
    帖最后由
    0.52
    참고
    0.50
     estekak
    0.50
    Activations Density 0.028%

    No Known Activations