© 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. 36-GEMMASCOPE-RES-16K
    11. 9619
    Prev
    Next
    INDEX
    Explanations

    references to programming languages or programming-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    您
    -0.90
    如果您
    -0.73
     لكم
    -0.73
    您可以
    -0.72
     לכם
    -0.72
    Usted
    -0.71
    您的
    -0.71
     usted
    -0.71
    为您
    -0.69
     vostro
    -0.68
    POSITIVE LOGITS
     thou
    1.23
     thy
    1.05
     ты
    0.96
     твои
    0.93
     твое
    0.92
     тебе
    0.88
    Ты
    0.87
     можешь
    0.87
     твоя
    0.86
     Thou
    0.85
    Activations Density 0.189%

    No Known Activations