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. 21-GEMMASCOPE-RES-16K
    6. 3046
    Prev
    Next
    INDEX
    Explanations

    terms related to diabetes and metabolic disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.61
    GEBURTS
    -0.57
    piram
    -0.56
     Jurí
    -0.55
     beginnetje
    -0.53
     سكانية
    -0.53
    رشف
    -0.52
    awtextra
    -0.52
     <>",
    -0.51
     Muf
    -0.50
    POSITIVE LOGITS
     diabetes
    1.60
     Diabetes
    1.58
     insulin
    1.52
    Diabetes
    1.44
     glucose
    1.43
     diabetic
    1.41
     diabetics
    1.41
    diabetes
    1.34
     Insulin
    1.33
    Insulin
    1.29
    Activations Density 0.464%

    No Known Activations