© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15720
    Prev
    Next
    INDEX
    Explanations

    references to racial or ethnic identities and the perceptions surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.90
     ModelExpression
    -0.71
    tagHelperRunner
    -0.65
    脚注の使い方
    -0.57
    complexContent
    -0.57
    MessageTagHelper
    -0.57
    ViewImports
    -0.56
    findpost
    -0.55
    aarrggbb
    -0.53
     <<<<<<<<<<<<<<
    -0.53
    POSITIVE LOGITS
    řez
    0.36
    iric
    0.33
    ricultural
    0.32
    BibitemShut
    0.32
    roir
    0.32
    MERCIAL
    0.32
    requireNonNull
    0.31
     lizenz
    0.31
    bbons
    0.31
     dé
    0.31
    Activations Density 1.160%

    No Known Activations