© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1024
    Prev
    Next
    INDEX
    Explanations

    biochemical compounds and their metabolic roles

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

    TCA cycle intermediates and related metabolites

    np_acts-logits-general · gemini-2.0-flash

    acid, lactic, fermentation, pyruvate, ketones

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     jspb
    -0.59
    IVEREF
    -0.54
     Daf
    -0.49
    argout
    -0.49
    webElement
    -0.48
    Abitanti
    -0.47
    webElementXpaths
    -0.46
    Daf
    -0.44
     linkovi
    -0.43
     ARK
    -0.43
    POSITIVE LOGITS
     pyruvate
    0.77
    ruvate
    0.72
     ketones
    0.72
     ExecuteAsync
    0.69
     ketone
    0.68
     Ket
    0.67
     acetone
    0.64
     fermentation
    0.64
    Acetone
    0.64
     lactic
    0.63
    Activations Density 0.635%

    No Known Activations