© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10796
    Prev
    Next
    INDEX
    Explanations

    references to programming errors and build issues in a coding context

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

    Code, file paths, or programming terms

    np_acts-logits-general · gemini-2.0-flash

    ビルド in maven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beliau
    -0.40
     Egipto
    -0.34
     
    -0.32
    ็ต
    -0.29
     invitación
    -0.29
    /
    -0.28
     creencias
    -0.28
     i
    -0.28
     dirigida
    -0.28
     Kreise
    -0.28
    POSITIVE LOGITS
    ьаж
    1.07
     propOrder
    1.00
    ロウィン
    1.00
    MessageOf
    0.97
    parsedMessage
    0.96
    <unused8>
    0.94
    <unused43>
    0.93
    <unused79>
    0.93
    <unused41>
    0.93
    <unused17>
    0.93
    Activations Density 0.024%

    No Known Activations