© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8627
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to computer programming and data structures

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

    Code, math, or file-related strings

    np_acts-logits-general · gemini-2.0-flash

    foreign language words and symbols

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enumi
    -0.71
    ;\\
    -0.68
     themſelves
    -0.66
    posables
    -0.66
     mohair
    -0.65
     Conſ
    -0.62
     dAtA
    -0.62
     myſelf
    -0.62
     Efq
    -0.60
     againſt
    -0.60
    POSITIVE LOGITS
    同上
    0.82
    同じく
    0.78
     szint
    0.77
    Tembelea
    0.76
    —
    0.74
    SourceChecksum
    0.74
    Välislingid
    0.71
    Personensuche
    0.70
    errHandler
    0.69
    protoc
    0.68
    Activations Density 2.430%

    No Known Activations