© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1974
    Prev
    Next
    INDEX
    Explanations

    references to heat shock proteins and their interactions in biological systems

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

    HSP folding protein

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     виправивши
    -0.64
    ymce
    -0.57
     TSI
    -0.52
     Obispo
    -0.50
    PhysRevLett
    -0.48
    Toro
    -0.47
    urem
    -0.47
     wünsche
    -0.46
    simum
    -0.45
    kema
    -0.45
    POSITIVE LOGITS
     chaper
    0.92
     Folding
    0.78
     folding
    0.78
     unfolded
    0.74
    folding
    0.69
    Folding
    0.69
    folded
    0.66
     protein
    0.65
     Heat
    0.65
    MigrationBuilder
    0.64
    Activations Density 0.498%

    No Known Activations