© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    dependencies and conditions related to quantity, success, and performance in various contexts

    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
    :✨
    -0.39
    대로
    -0.36
    adel
    -0.35
    DockStyle
    -0.34
    "?>
    -0.34
    dacia
    -0.33
    ControllerAdvice
    -0.33
    商品説明
    -0.32
    jMenuItem
    -0.32
     consistente
    -0.32
    POSITIVE LOGITS
     depends
    1.17
     depend
    0.97
     dépend
    0.86
     Depends
    0.86
    depends
    0.85
    Depends
    0.83
     largely
    0.82
     Depend
    0.79
     depende
    0.76
     dipende
    0.76
    Activations Density 0.428%

    No Known Activations