© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3600
    Prev
    Next
    INDEX
    Explanations

    programming-related code snippets or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ElementException
    -0.62
     }}"></
    -0.59
    :✨
    -0.58
     RoutedEventArgs
    -0.58
     архивлан
    -0.56
    RenderAtEndOf
    -0.53
    InitStruct
    -0.52
    WireFormatLite
    -0.50
    țul
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
    #+#
    0.57
    ponge
    0.56
     bcrypt
    0.54
     féminine
    0.51
    bcrypt
    0.48
    macher
    0.47
    issau
    0.47
    pointed
    0.47
     Plummer
    0.46
    )_/¯
    0.45
    Activations Density 0.065%

    No Known Activations