© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7883
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting and tracking software bugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ፩
    -0.57
    argout
    -0.56
    Демографія
    -0.52
    Попис
    -0.50
    nodoc
    -0.50
    styleType
    -0.48
    MLLoader
    -0.48
    Зачем
    -0.47
    HtmlAttribute
    -0.46
    MergeFrom
    -0.46
    POSITIVE LOGITS
     workaround
    0.96
     troubleshooting
    0.86
     bug
    0.79
     reproduce
    0.73
     reproduced
    0.69
     reproducing
    0.69
     reproducible
    0.69
     troubleshoot
    0.68
     bugs
    0.68
     issue
    0.68
    Activations Density 0.884%

    No Known Activations