© 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. 386
    Prev
    Next
    INDEX
    Explanations

    occurrences of special characters or formatting markers in text

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

    the beginning of a section or paragraph in the text

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

    multi-language technical terms

    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
     ég
    -0.52
    sizeCache
    -0.50
    industria
    -0.47
     otomatig
    -0.47
     unknownFields
    -0.46
     legitimacy
    -0.46
    THON
    -0.44
    uled
    -0.44
     Inscrivez
    -0.43
    addGap
    -0.43
    POSITIVE LOGITS
    Архівовано
    0.68
     للمعارف
    0.67
    脚注の使い方
    0.65
    外部リンク
    0.61
    TemporalType
    0.61
     المعرف
    0.60
     OFDb
    0.60
    databind
    0.60
    amssymb
    0.59
    paravant
    0.59
    Activations Density 0.277%

    No Known Activations