© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15083
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structural components of a webpage

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

    HTML or XML tags/attributes

    np_acts-logits-general · gemini-2.0-flash

    localization strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للاسماء
    -0.45
     חיצוניים
    -0.43
    drawSprites
    -0.37
     !$
    -0.36
    مصادر
    -0.36
    ResumeLayout
    -0.36
    burgs
    -0.34
    ніципалі
    -0.34
    ứt
    -0.34
    Besos
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.65
    AndEndTag
    0.45
    iasaan
    0.43
     Kräuter
    0.43
    HtmlAttribute
    0.42
     Información
    0.41
    Identyfik
    0.40
     Sosial
    0.40
     Jurí
    0.40
    farb
    0.39
    Activations Density 0.140%

    No Known Activations