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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1828
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to software commands and operations, particularly in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.60
    ContentAsync
    -0.60
     AppModule
    -0.59
    fpm
    -0.59
    HasColumnType
    -0.58
    GEBURTSDATUM
    -0.57
    __(/*!
    -0.57
    LEADING
    -0.56
    contentLoaded
    -0.56
    (!__
    -0.56
    POSITIVE LOGITS
     שוליים
    0.59
    XmlAccessType
    0.58
     ModelExpression
    0.57
    تفصیلات
    0.56
    észetes
    0.52
     كومونز
    0.52
     sumpay
    0.52
    󠁣
    0.49
    хіво
    0.49
    AnchorStyles
    0.48
    Activations Density 0.128%

    No Known Activations