© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1933
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and identifiers

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

    programming code syntax and identifiers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    )+(
    -0.33
    ായി
    -0.31
     pay
    -0.31
     true
    -0.28
     mut
    -0.28
     fo
    -0.28
     mutual
    -0.27
     free
    -0.27
     conter
    -0.27
     thank
    -0.26
    POSITIVE LOGITS
     مشين
    1.02
    parsedMessage
    0.95
    Personendaten
    0.91
     ProtoMessage
    0.91
    RenderAtEndOf
    0.87
     autorytatywna
    0.73
    Diwedd
    0.73
    SharedCtor
    0.72
    ValueStyle
    0.70
     المعيارى
    0.70
    Activations Density 1.693%

    No Known Activations