© 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. 31-GEMMASCOPE-RES-16K
    11. 12292
    Prev
    Next
    INDEX
    Explanations

    URL patterns and localization parameters in web addresses

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

    language and locale identifiers in URLs and code (such as "en-US", "fr-gp", "ja_JP").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.82
     مشين
    -0.68
     Administrativna
    -0.63
     Autorizaciones
    -0.62
     typelib
    -0.61
    migrationBuilder
    -0.61
    UnusedPrivate
    -0.60
    WithIOException
    -0.60
     ModelExpression
    -0.60
    queryInterface
    -0.59
    POSITIVE LOGITS
     en
    1.21
    en
    0.92
     EN
    0.83
    EN
    0.80
     US
    0.62
     En
    0.61
    En
    0.60
     fr
    0.56
     UK
    0.54
     zh
    0.54
    Activations Density 0.509%

    No Known Activations