Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13465
    Prev
    Next
    INDEX
    Explanations

    occurrences of document type definitions and schema declarations in markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.04
    verwijspagina
    -0.87
     Wiktionnaire
    -0.80
     ویکی‌پدیا
    -0.77
    PerformLayout
    -0.72
    Portale
    -0.69
    himovic
    -0.68
     bpy
    -0.68
    Abitanti
    -0.67
    hagy
    -0.67
    POSITIVE LOGITS
    DOCTYPE
    1.01
    HtmlAttribute
    0.87
     ModelExpression
    0.84
    pdf
    0.75
     وتسجيلات
    0.69
    fontWeight
    0.66
    eqn
    0.66
    migrations
    0.62
    doctype
    0.61
    BackColor
    0.61
    Activations Density 0.014%

    No Known Activations