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

    Neuronpedia

    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. 16-GEMMASCOPE-RES-16K
    11. 9619
    Prev
    Next
    INDEX
    Explanations

    programming code elements and function calls

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

    Code snippets containing "exit"

    np_acts-logits-general · gemini-2.0-flash

    program exit commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //}
    -0.39
     ناح
    -0.38
    Norton
    -0.38
    Track
    -0.38
     preferencias
    -0.37
    CompleteListener
    -0.37
    akyti
    -0.37
    NSON
    -0.37
    zene
    -0.37
    //};
    -0.37
    POSITIVE LOGITS
     exit
    1.12
    exit
    1.06
     Exit
    1.04
    contentLoaded
    0.93
     AssemblyCulture
    0.91
     EXIT
    0.88
    Exit
    0.87
    quit
    0.85
    退出
    0.83
     exits
    0.83
    Activations Density 0.200%

    No Known Activations