© 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. 31-GEMMASCOPE-RES-16K
    11. 4699
    Prev
    Next
    INDEX
    Explanations

    programming concepts and boolean logic statements

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

    words that connect clauses or express conditional/causal relationships across multiple languages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.57
    jsonwebtoken
    -0.54
    RenderAtEndOf
    -0.53
     ujednoznacz
    -0.52
     שוליים
    -0.52
    polation
    -0.50
     leſs
    -0.50
    COUVER
    -0.50
     itſelf
    -0.48
    uhi
    -0.48
    POSITIVE LOGITS
     there
    0.67
     occurs
    0.62
     occurred
    0.58
     emerges
    0.56
     arises
    0.55
     occur
    0.54
     are
    0.52
     prevails
    0.52
     happens
    0.50
     terdapat
    0.50
    Activations Density 0.087%

    No Known Activations