© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in the context of contributions or acknowledgments

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

    proper nouns and names associated with Māori culture

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

    Māori, Aorangi, tika, fix zippers

    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
     estekak
    -0.92
    UnusedPrivate
    -0.83
    ьаж
    -0.79
     ſy
    -0.78
     nakalista
    -0.76
     pleaſure
    -0.75
     تضيفلها
    -0.74
     سكانية
    -0.74
     fubject
    -0.74
     ModelExpression
    -0.73
    POSITIVE LOGITS
     culturelles
    0.52
     Ka
    0.52
     munka
    0.49
    ui
    0.49
     exécu
    0.48
     sozinho
    0.46
     L
    0.46
     řekl
    0.45
     H
    0.45
     popolo
    0.44
    Activations Density 0.061%

    No Known Activations