© 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. 9741
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to HTML structure

    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
     MaterialApp
    -0.70
    PRNewswire
    -0.70
    ագրություններ
    -0.67
    最快更新
    -0.66
     geweest
    -0.62
    beforeEach
    -0.61
    GraphicsUnit
    -0.61
    AccessorTable
    -0.61
    WebElementEntity
    -0.60
     Leyden
    -0.60
    POSITIVE LOGITS
    REASONS
    2.91
     REASONS
    1.98
    Reasons
    1.54
     Reasons
    1.50
     reasons
    1.41
    reasons
    1.39
    Reason
    1.21
     Reason
    1.17
     reason
    1.16
    reason
    1.06
    Activations Density 0.013%

    No Known Activations