© 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. 315
    Prev
    Next
    INDEX
    Explanations

    references to licenses and usage permissions related to software files

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

    terms related to licensing and file usage conditions

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

    file except

    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
    WithIOException
    -0.75
     considérons
    -0.64
    󠁮
    -0.61
     arşivlendi
    -0.57
    évaluateur
    -0.57
    脚注の使い方
    -0.56
    urtstag
    -0.54
     समीक्षक
    -0.54
    MigrationBuilder
    -0.54
     дописавши
    -0.54
    POSITIVE LOGITS
     estekak
    0.49
     pack
    0.45
    SaveVideo
    0.42
    ობ
    0.42
     packs
    0.42
    pack
    0.40
     Audiodateien
    0.40
     fusion
    0.40
    貫
    0.40
    hyrchwyd
    0.40
    Activations Density 0.080%

    No Known Activations