© 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. 1-GEMMASCOPE-RES-16K
    11. 16313
    Prev
    Next
    INDEX
    Explanations

    words related to covering or wrapping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endorsement
    -0.61
    شهاد
    -0.57
    hen
    -0.55
    iesta
    -0.54
     charge
    -0.53
    TypedDataSet
    -0.50
     karma
    -0.49
    стере
    -0.49
     interference
    -0.49
     infil
    -0.48
    POSITIVE LOGITS
     covering
    1.03
     covered
    0.89
     Covering
    0.86
     covers
    0.85
     wrapped
    0.78
    PerformLayout
    0.78
    covered
    0.78
    Covers
    0.77
     ویکی‌پدیا
    0.74
    Covered
    0.74
    Activations Density 0.067%

    No Known Activations