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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5792
    Prev
    Next
    INDEX
    Explanations

    punctuation and indicators of lists or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{
    -0.38
     Hurst
    -0.33
     Helm
    -0.32
    ISupport
    -0.31
     Kes
    -0.30
     ár
    -0.30
     Financial
    -0.30
     Salary
    -0.29
     Office
    -0.29
     imperial
    -0.29
    POSITIVE LOGITS
     podró
    0.68
     nemlig
    0.60
    RectangleBorder
    0.60
    ​—
    0.59
     tričko
    0.58
    bootstrapcdn
    0.58
     découver
    0.57
    archiwizowane
    0.56
    aarrggbb
    0.56
    ſſo
    0.56
    Activations Density 0.482%

    No Known Activations