© 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. 24-GEMMASCOPE-RES-16K
    11. 10222
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming errors and issues with code execution

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

    The token before "fail" or "fails"

    np_acts-logits-general · gemini-2.0-flash

    crash or failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.60
     auguri
    -0.56
    __":
    -0.53
    それだけ
    -0.52
     מוכ
    -0.51
     protoimpl
    -0.48
    égias
    -0.48
    MigrationBuilder
    -0.47
     незавершена
    -0.47
    __":
    -0.47
    POSITIVE LOGITS
     crash
    0.91
     crashes
    0.87
     crashed
    0.84
     crashing
    0.83
    crash
    0.82
    cras
    0.80
     incorrectly
    0.79
     corrupt
    0.78
     messed
    0.78
     broke
    0.77
    Activations Density 0.847%

    No Known Activations