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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15197
    Prev
    Next
    INDEX
    Explanations

    terms and concepts specifically related to diabetes and its medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.99
     endregion
    -0.70
    TagHelper
    -0.68
    rilis
    -0.64
    Kesimpulan
    -0.63
     fermés
    -0.62
    æder
    -0.57
     senso
    -0.56
    AddTagHelper
    -0.55
    LayoutStyle
    -0.55
    POSITIVE LOGITS
     Sho
    1.16
    Sho
    1.08
     sho
    0.96
    sho
    0.96
     diabetes
    0.81
    Diabetes
    0.68
     Diabetes
    0.67
    Shop
    0.66
    operatorname
    0.62
    ↳
    0.59
    Activations Density 0.141%

    No Known Activations