© 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. 3-GEMMASCOPE-RES-16K
    11. 1318
    Prev
    Next
    INDEX
    Explanations

    keywords related to exceptions and error handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.66
     esternos
    -0.63
    SourceChecksum
    -0.57
     nämlich
    -0.56
     totiž
    -0.56
     المعيارى
    -0.56
     magasiner
    -0.55
     OFDb
    -0.55
    Locality
    -0.55
    észetes
    -0.53
    POSITIVE LOGITS
    throw
    3.33
     throw
    2.21
     Throw
    2.02
    Throw
    1.91
     throws
    1.59
     throwing
    1.57
     Throws
    1.55
    throwing
    1.51
    throws
    1.50
     threw
    1.49
    Activations Density 0.037%

    No Known Activations