© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 937
    Prev
    Next
    INDEX
    Explanations

    sequences of symbols or characters commonly used in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -1.15
     Infórmanos
    -0.94
    webElementXpaths
    -0.92
    Vidite
    -0.91
     Numerade
    -0.89
     propOrder
    -0.89
    (!__
    -0.87
     InputDecoration
    -0.86
     nakalista
    -0.86
     EconPapers
    -0.85
    POSITIVE LOGITS
     
    0.66
      
    0.61
    们
    0.54
    0.52
    ย์
    0.47
     final
    0.47
    +

    0.46
    </em>
    0.46
     start
    0.45
     main
    0.45
    Activations Density 0.076%
    No Known Activations