© 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. 22-GEMMASCOPE-RES-16K
    11. 12753
    Prev
    Next
    INDEX
    Explanations

    user interface features that enhance user experience and multitasking capabilities

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

    GUI or application settings and features

    np_acts-logits-general · gemini-2.0-flash

    desktop interface elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BindingResult
    -0.61
    scalatest
    -0.56
     tooth
    -0.48
     Olympedia
    -0.47
     wept
    -0.47
    /***/
    -0.46
     orgánico
    -0.46
    ChildScrollView
    -0.45
    TagHelper
    -0.45
     Stornier
    -0.45
    POSITIVE LOGITS
     launcher
    0.94
     wallpaper
    0.87
     taskbar
    0.84
     screens
    0.84
     Launcher
    0.83
     launchers
    0.80
     minimized
    0.78
     Wallpaper
    0.78
     tray
    0.78
     screen
    0.77
    Activations Density 0.369%

    No Known Activations