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. 117246
    Prev
    Next
    INDEX
    Explanations

    elements related to account verification processes within digital platforms

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

    Assignment operator (equals sign) in localization/internationalization string definition files, marking the boundary between string identifiers and their translated values.

    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
    Geplaatst
    -0.70
    MigrationBuilder
    -0.69
    الحياه
    -0.59
     ActivatedRoute
    -0.59
    ErrUnexpectedEOF
    -0.57
    脚注の使い方
    -0.57
    makeConstraints
    -0.57
     estekak
    -0.57
    XmlRootElement
    -0.56
    :✨
    -0.56
    POSITIVE LOGITS
    TPM
    0.36
    有
    0.34
    CST
    0.34
    夠
    0.34
    numerusform
    0.33
    printf
    0.33
    FPGA
    0.32
     =
    0.31
    noscript
    0.31
    DC
    0.31
    Activations Density 0.018%

    No Known Activations