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

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 13652
    Prev
    Next
    INDEX
    Explanations

    phrases that convey uncertainty or questions about identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.55
    InitVars
    -0.47
    //
    -0.42
    KommentareTeilen
    -0.41
    Spoljašnje
    -0.40
     surla
    -0.39
     ویکی‌پدیای
    -0.38
     iParam
    -0.38
    usercontent
    -0.38
    存于互联网档案馆
    -0.38
    POSITIVE LOGITS
     really
    3.75
    really
    3.36
    Really
    3.23
     Really
    3.14
     realmente
    2.91
     truly
    2.88
     vraiment
    2.81
     REALLY
    2.78
     wirklich
    2.69
     veramente
    2.67
    Activations Density 0.875%

    No Known Activations