© 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. 72
    Prev
    Next
    INDEX
    Explanations

    numerical references and citations

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

    references to academic citations or identifiers

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

    scientific citations and links

    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
    XmlAccessorType
    -0.74
     <>",
    -0.73
     réessayer
    -0.70
    MessageOf
    -0.63
    ?}",
    -0.61
     насељу
    -0.61
    ImageContext
    -0.61
    adpleegd
    -0.60
     scolaires
    -0.60
    ;->
    -0.59
    POSITIVE LOGITS
    endphp
    0.57
    Bronnen
    0.56
    Orm
    0.55
    httphttps
    0.50
     Yah
    0.48
     BorderSide
    0.47
    byes
    0.47
     الحره
    0.46
     SqlDbType
    0.46
     capito
    0.45
    Activations Density 0.022%

    No Known Activations