© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8786
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to molecular biology and laboratory procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millions
    -0.50
    reif
    -0.47
    фак
    -0.47
    ঙ্
    -0.46
    tt
    -0.46
    sp
    -0.45
    靠
    -0.45
    gob
    -0.45
    io
    -0.45
     लाख
    -0.43
    POSITIVE LOGITS
    writeFieldEnd
    0.83
     ModelExpression
    0.83
    الحياه
    0.83
    sizeCache
    0.81
     мәкал
    0.78
    webElementXpaths
    0.76
    Попис
    0.75
    setVerticalGroup
    0.75
    ViewFeatures
    0.73
    yntaxException
    0.72
    Activations Density 3.317%

    No Known Activations