Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 779
    Prev
    Next
    INDEX
    Explanations

    references to Wi-Fi technology

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

    references to Wi-Fi technology

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

    Wi-Fi

    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
     assi
    -0.60
    gamesh
    -0.57
     Hallen
    -0.52
     Assim
    -0.51
     celle
    -0.49
     raison
    -0.49
    lijk
    -0.48
     Tugend
    -0.48
     Varma
    -0.48
     crossorigin
    -0.48
    POSITIVE LOGITS
     Wi
    0.74
     wi
    0.71
    Wi
    0.69
    AccessorTable
    0.62
    reportWebVitals
    0.61
     FormsModule
    0.58
    ThroughAttribute
    0.54
    glom
    0.54
     baseman
    0.54
     CommandType
    0.54
    Activations Density 0.004%

    No Known Activations