© 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. 1758
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biochemical processes and experimental procedures

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

    photographic film exposure

    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
    
    -0.63
     تضيفلها
    -0.58
    stdc
    -0.57
    StringCopy
    -0.57
     Siri
    -0.57
    SequentialGroup
    -0.56
    jerg
    -0.55
     EconPapers
    -0.52
     Allein
    -0.51
    RepeatedField
    -0.50
    POSITIVE LOGITS
     exposure
    0.84
    Exposure
    0.81
     Exposure
    0.80
     exposing
    0.78
     expose
    0.74
     EXPOSURE
    0.74
     exposures
    0.71
     exposición
    0.70
     exposes
    0.69
    exposure
    0.69
    Activations Density 0.315%

    No Known Activations