© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biomarkers and clinical diagnostics

    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
     perchè
    -1.30
     Whilst
    -1.08
     poichè
    -1.07
    Whilst
    -1.05
     shewn
    -1.00
     Amongst
    -0.98
     whilst
    -0.92
     diatas
    -0.92
     shew
    -0.88
    の為
    -0.88
    POSITIVE LOGITS
     TABLE
    0.71
     nonzero
    0.70
    Ϫ
    0.69
    —
    0.68
     FIGURE
    0.68
     nonnegative
    0.68
     nont
    0.64
     nons
    0.64
    ◗
    0.63
    さまざまな
    0.62
    Activations Density 5.003%

    No Known Activations