© 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. 73
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to dental hygiene and removable dental appliances

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

    instructions related to temperature control and shading

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

    Orthodontists, braces

    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
    SuppressLint
    -0.55
     تانيه
    -0.55
     Unlocked
    -0.55
    abestanden
    -0.54
    openqa
    -0.53
    .~(\
    -0.52
     JsonObject
    -0.51
    mybatisplus
    -0.50
    ItemGroup
    -0.50
     embal
    -0.49
    POSITIVE LOGITS
     shutters
    0.88
     blinds
    0.87
     shutter
    0.73
     Blinds
    0.67
     Venetian
    0.66
     curtains
    0.66
     braces
    0.63
     blind
    0.62
     Blind
    0.61
     blin
    0.60
    Activations Density 0.148%

    No Known Activations