© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13198
    Prev
    Next
    INDEX
    Explanations

    variability and differences in medical and clinical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.66
    recated
    -0.50
    TagMode
    -0.45
    zieży
    -0.42
     lenker
    -0.42
    хьтан
    -0.41
     ComVisible
    -0.40
    Кру
    -0.40
    jande
    -0.39
     Paglinawan
    -0.39
    POSITIVE LOGITS
     variation
    2.55
     variations
    2.45
     Variation
    2.28
    variation
    2.19
     Variations
    2.19
     variability
    2.14
    Variation
    2.14
     vary
    2.13
    variations
    2.11
     varia
    2.03
    Activations Density 1.188%

    No Known Activations