© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 239
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "he" or variations of it

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

    mentions of the element helium

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

    helium, rhegulin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    
    -0.62
    AccessorTable
    -0.48
    м
    -0.47
     חיצוניים
    -0.46
     Liquids
    -0.44
    Lw
    -0.43
    аза
    -0.43
    at
    -0.43
     Genes
    -0.42
     tôm
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.79
     فريبيس
    0.69
     الرياضيه
    0.69
    出版年
    0.69
    ✨:
    0.68
    parsedMessage
    0.65
    }{*}{
    0.64
    twimg
    0.62
    abetes
    0.61
     poiv
    0.61
    Activations Density 0.125%

    No Known Activations