© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    specific interactions or transformations in a complex biochemical context

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

    Fructose-bisphosphate aldolase (FBA) and related enzymes

    np_acts-logits-general · gemini-2.0-flash

    Genshin Impact characters

    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
    ThroughAttribute
    -0.52
     penicillin
    -0.52
     Kaspar
    -0.51
    สบ
    -0.49
     Brandy
    -0.49
     Fulda
    -0.47
    GEBURTSDATUM
    -0.47
    killer
    -0.44
     unicorn
    -0.44
    Morfo
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.72
    uxxxx
    0.71
    原神
    0.68
     Genshin
    0.65
    IsMutable
    0.64
     Klee
    0.60
    addCriterion
    0.60
     ehe
    0.57
    OrNil
    0.57
    魈
    0.57
    Activations Density 0.107%

    No Known Activations