© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15625
    Prev
    Next
    INDEX
    Explanations

    code snippets related to window setup and event handling in graphical programming

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

    Code errors or error handling

    np_acts-logits-general · gemini-2.0-flash

    closing or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$?
    -0.55
    GTCX
    -0.52
    tomy
    -0.50
    WEBPACK
    -0.50
    Parcelize
    -0.50
    ISPR
    -0.49
     typename
    -0.48
    AntiForgeryToken
    -0.48
    шкан
    -0.47
    /******/
    -0.47
    POSITIVE LOGITS
    Quit
    0.63
    quit
    0.62
     quit
    0.55
    
    0.54
    windowFixed
    0.54
     quitting
    0.53
     autorytatywna
    0.53
    tudo
    0.52
    TTF
    0.52
     Hyp
    0.51
    Activations Density 0.428%

    No Known Activations