© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31119
    Prev
    Next
    INDEX
    Explanations

    references to exceptions and error messages in programming contexts

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

    exception occurs or said

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setViewportView
    -0.81
    httphttps
    -0.76
     commerciali
    -0.73
     للاسماء
    -0.72
     useRouter
    -0.71
     Bretaña
    -0.71
    rrggbb
    -0.71
     بيها
    -0.69
     '\\;'
    -0.68
     soldati
    -0.66
    POSITIVE LOGITS
     Exception
    0.93
    EXCEPTION
    0.80
    Exception
    0.80
     exception
    0.79
    exception
    0.76
     Stande
    0.69
     Exceptions
    0.69
     exceptions
    0.66
    anian
    0.66
    SSE
    0.65
    Activations Density 0.011%

    No Known Activations