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 - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4876
    Prev
    Next
    INDEX
    Explanations

    references to "window" in a programming or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variés
    -0.82
     grze
    -0.80
     recentes
    -0.80
     découver
    -0.76
    agissait
    -0.76
     loisirs
    -0.74
     espirituales
    -0.74
     vostri
    -0.74
     prácti
    -0.73
     élect
    -0.72
    POSITIVE LOGITS
     window
    1.55
     windows
    1.51
     Window
    1.47
    window
    1.33
     WINDOW
    1.33
     Windows
    1.33
    windows
    1.29
    Windows
    1.28
    Window
    1.24
    WINDOW
    1.21
    Activations Density 0.041%

    No Known Activations