© 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. 10-GEMMASCOPE-RES-16K
    11. 5812
    Prev
    Next
    INDEX
    Explanations

    instances of rendering-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -1.01
     connaissent
    -0.81
    AsUp
    -0.76
     axios
    -0.73
    lotz
    -0.71
    Specifiche
    -0.70
    ajiban
    -0.70
     year
    -0.69
     KeyError
    -0.69
     Sykes
    -0.68
    POSITIVE LOGITS
     render
    1.67
     Render
    1.66
    render
    1.58
    Render
    1.56
     rendering
    1.42
    RENDER
    1.40
     renders
    1.39
     rendered
    1.38
    rendered
    1.20
    renders
    1.20
    Activations Density 0.046%

    No Known Activations