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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8347
    Prev
    Next
    INDEX
    Explanations

    terms related to glucose metabolism and its regulation

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

    glucose metabolism and homeostasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    렷
    -0.48
    ValueStyle
    -0.47
    ryk
    -0.47
    AnchorStyles
    -0.45
    ThroughAttribute
    -0.44
     intptr
    -0.43
    เยอะ
    -0.42
    อัน
    -0.42
     far
    -0.42
     part
    -0.41
    POSITIVE LOGITS
     Glucose
    1.28
    Glucose
    1.23
     glucose
    1.22
    glucose
    1.09
     GLC
    0.71
    glycemia
    0.66
     getchar
    0.63
    cinfo
    0.60
    chengladbach
    0.59
     glucos
    0.59
    Activations Density 0.020%

    No Known Activations