© 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. 15402
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and syntax errors

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

    Code errors related to exceptions

    np_acts-logits-general · gemini-2.0-flash

    throw or log exception

    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
     home
    -0.65
    home
    -0.59
     haupts
    -0.55
    mainMenu
    -0.55
     main
    -0.55
     MAIN
    -0.53
    main
    -0.53
    Home
    -0.51
     arrivals
    -0.51
    MAIN
    -0.50
    POSITIVE LOGITS
    throw
    1.90
     throw
    1.61
     throwing
    1.23
     Throw
    1.17
     threw
    1.17
     throws
    1.14
    raise
    1.13
    Throw
    1.07
     Throwing
    1.04
    throwing
    1.03
    Activations Density 0.066%

    No Known Activations