© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12269
    Prev
    Next
    INDEX
    Explanations

    references to "windows" or window-related contexts in technical or narrative descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.90
    AndEndTag
    -0.89
     initComponents
    -0.88
     myſelf
    -0.87
     defaultstate
    -0.87
    XtraReports
    -0.86
     Efq
    -0.84
    ftagPool
    -0.84
     فريبيس
    -0.83
    ConstraintMaker
    -0.82
    POSITIVE LOGITS
     windows
    0.81
     train
    0.79
     window
    0.78
     Windows
    0.70
    Train
    0.68
    windows
    0.67
    train
    0.65
     Train
    0.65
    Windows
    0.62
     Window
    0.58
    Activations Density 0.115%

    No Known Activations