© 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. 15812
    Prev
    Next
    INDEX
    Explanations

    error handling and exception management code patterns

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

    Error handling and exceptions ("catch")

    np_acts-logits-general · gemini-2.0-flash

    try catch error

    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
    BagLayout
    -0.49
     Came
    -0.47
     connexes
    -0.46
    #![
    -0.45
     OrderedDict
    -0.44
    Came
    -0.44
    ไม
    -0.44
     bland
    -0.43
     blessed
    -0.43
    bygg
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.84
    oredCriteria
    0.75
    =$?
    0.75
     error
    0.74
     Error
    0.71
     NSError
    0.70
     AssemblyProduct
    0.66
     propOrder
    0.66
     Throwable
    0.66
    ंदीखरीदारी
    0.66
    Activations Density 0.030%

    No Known Activations