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. 20-GEMMASCOPE-RES-16K
    6. 6504
    Prev
    Next
    INDEX
    Explanations

    terms related to diabetes and its management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.56
    клопе
    -0.51
    liothèque
    -0.50
     <>",
    -0.49
    GEBURTS
    -0.49
    رشف
    -0.48
    ciato
    -0.47
     beginnetje
    -0.47
    piram
    -0.46
    AuthProvider
    -0.46
    POSITIVE LOGITS
     insulin
    1.71
     diabetes
    1.71
     Diabetes
    1.69
     glucose
    1.59
     diabetic
    1.58
    Diabetes
    1.56
     sugar
    1.55
     diabetics
    1.54
     Insulin
    1.48
    diabetes
    1.43
    Activations Density 0.584%

    No Known Activations