© 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. 39-GEMMASCOPE-RES-16K
    11. 4322
    Prev
    Next
    INDEX
    Explanations

    question marks and response indicators in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     why
    -0.43
     apakah
    -0.34
     warum
    -0.34
     does
    -0.32
     did
    -0.32
    آیا
    -0.29
     whoever
    -0.29
    這就是
    -0.28
    ViewImports
    -0.28
     maybe
    -0.28
    POSITIVE LOGITS
     How
    1.30
     What
    1.29
    How
    1.04
    What
    1.01
     Where
    0.91
     Which
    0.87
    Where
    0.78
     Who
    0.77
    httphttps
    0.72
    Which
    0.71
    Activations Density 0.389%

    No Known Activations