© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11109
    Prev
    Next
    INDEX
    Explanations

    references to tabs and tab controls within the context of user interface design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lowry
    -0.86
    </h1>
    -0.70
     Fried
    -0.68
     Kongo
    -0.67
     Weston
    -0.66
     more
    -0.65
     postId
    -0.64
    machung
    -0.63
     Wiese
    -0.63
    FWD
    -0.63
    POSITIVE LOGITS
     tabs
    1.36
     Tabs
    1.33
     TAP
    1.28
    StructEnd
    1.22
     Tab
    1.20
    addTab
    1.18
     tab
    1.18
    Tab
    1.17
    tabs
    1.15
     tap
    1.14
    Activations Density 0.132%

    No Known Activations