© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13338
    Prev
    Next
    INDEX
    Explanations

    references to the Windows operating system

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

    "Windows" or Microsoft technologies

    np_acts-logits-general · gemini-2.0-flash

    Windows UI XAML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.68
    <bos>
    -0.63
     tartalomajánló
    -0.58
     leksikon
    -0.53
    zini
    -0.51
     دیکھیے
    -0.50
    addto
    -0.49
     Biôgrafia
    -0.49
    }{*}{}
    -0.49
     peny
    -0.48
    POSITIVE LOGITS
    Windows
    1.21
     Windows
    0.97
    windows
    0.94
    Xaml
    0.94
     WINDOWS
    0.86
     Teut
    0.70
     "..\..\
    0.70
     windows
    0.69
    WINDOWS
    0.66
    indows
    0.66
    Activations Density 0.011%

    No Known Activations