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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3057
    Prev
    Next
    INDEX
    Explanations

    references to windows and related concepts in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     découver
    -0.83
     médicaux
    -0.82
     passés
    -0.81
     espirituales
    -0.79
     variés
    -0.77
     électro
    -0.76
     recentes
    -0.76
     âgées
    -0.75
    agissait
    -0.74
     trouvent
    -0.74
    POSITIVE LOGITS
     window
    1.54
     windows
    1.53
     Window
    1.41
    window
    1.31
    windows
    1.29
     WINDOW
    1.24
     Windows
    1.24
    Windows
    1.23
    Window
    1.18
    fenster
    1.18
    Activations Density 0.046%

    No Known Activations