© 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. 3828
    Prev
    Next
    INDEX
    Explanations

    terms related to proteins and their structures, particularly those involving folding and domains

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

    "Folds", "folded", or "curled"

    np_acts-logits-general · gemini-2.0-flash

    folding and curling

    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
     ExecuteAsync
    -0.83
    hares
    -0.64
    simum
    -0.59
     FIF
    -0.58
    lague
    -0.57
    طاء
    -0.56
    ibase
    -0.55
    shimano
    -0.54
     Ehren
    -0.54
    Titus
    -0.54
    POSITIVE LOGITS
     folds
    1.12
     fold
    1.09
     Fold
    1.05
     folded
    1.02
     folding
    0.98
    Fold
    0.97
     Folding
    0.88
    Folding
    0.88
    折り
    0.87
     wrinkle
    0.86
    Activations Density 0.324%

    No Known Activations