Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 11310
    Prev
    Next
    INDEX
    Explanations

    terms that relate to diabetes and its complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othelioma
    -0.78
    awtextra
    -0.74
    parseFrom
    -0.66
    Tek
    -0.64
    RegistryLite
    -0.63
    Nemo
    -0.62
     Tek
    -0.61
     Kenney
    -0.61
    Ό
    -0.60
     Gy
    -0.60
    POSITIVE LOGITS
     sugars
    1.52
     sugar
    1.50
     Diabetes
    1.44
     Sugar
    1.40
     diabetes
    1.38
     glucose
    1.37
    Glucose
    1.34
     SUGAR
    1.33
    Sugar
    1.33
     Glucose
    1.31
    Activations Density 0.446%

    No Known Activations