© 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. 6
    Prev
    Next
    INDEX
    Explanations

    instances of fainting or loss of consciousness

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

    references to physical altercations or instances of being incapacitated

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

    fainting or falling

    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
    IUrlHelper
    -0.72
    IsContent
    -0.69
     Administrativna
    -0.67
     AssemblyCompany
    -0.64
     שוליים
    -0.60
    entiary
    -0.60
     AssemblyTitle
    -0.59
    таратура
    -0.57
    sizeCache
    -0.56
    іга
    -0.56
    POSITIVE LOGITS
     fainted
    1.39
     unconscious
    1.36
     fainting
    1.23
     faint
    0.96
     consciousness
    0.94
     collapsed
    0.92
    consciousness
    0.88
     fain
    0.88
     knocked
    0.86
     blackout
    0.86
    Activations Density 0.108%

    No Known Activations