© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 326
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms related to insulin and glucose metabolism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    insulin and insulin resistance

    np_acts-logits-general · gemini-2.0-flash

    insulin sensitivity, resistance, signaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رشف
    -0.61
    клопе
    -0.58
     ***!
    -0.58
    Kaynakça
    -0.56
    CopyWith
    -0.56
    usitis
    -0.56
    oredCriteria
    -0.56
     protoimpl
    -0.55
     мәкал
    -0.54
    piram
    -0.53
    POSITIVE LOGITS
     insulin
    1.49
     Insulin
    1.36
     Diabetes
    1.27
    insulin
    1.27
    Insulin
    1.26
     diabetes
    1.19
    Diabetes
    1.19
     glucose
    1.17
     Glucose
    1.06
     diabetics
    1.06
    Activations Density 0.572%

    No Known Activations