© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3533
    Prev
    Next
    INDEX
    Explanations

    terms related to frogs and their reproductive biology, particularly in the context of hibernation and environmental influences

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

    Frogs and amphibians

    np_acts-logits-general · gemini-2.0-flash

    frogs and toads

    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
    évaluateur
    -0.64
    SequentialGroup
    -0.63
    tableFuture
    -0.60
    ultier
    -0.59
    #+#
    -0.58
    Tembelea
    -0.57
    !*\
    -0.57
     ब्रेकडाउन
    -0.55
     تانيه
    -0.54
     समीक्षाओं
    -0.54
    POSITIVE LOGITS
     frog
    0.98
     Frog
    0.96
     frogs
    0.95
     amphibians
    0.91
    Frog
    0.89
     tad
    0.89
    frog
    0.88
     Frogs
    0.84
     Toad
    0.81
     rana
    0.81
    Activations Density 0.212%

    No Known Activations