© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9499
    Prev
    Next
    INDEX
    Explanations

    code snippets involving web service interactions and data handling methods

    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
    featureID
    -0.80
    новништво
    -0.76
    RenderAtEndOf
    -0.75
    NameInMap
    -0.75
    存于互联网档案馆
    -0.74
    tvguidetime
    -0.73
    sidemargin
    -0.73
    RegressionTest
    -0.73
     Vikipedi
    -0.73
    didSet
    -0.72
    POSITIVE LOGITS
     cliquez
    0.41
    then
    0.40
     bagno
    0.40
     saj
    0.38
     Turnier
    0.37
    for
    0.37
     محل
    0.36
    Caret
    0.36
     
    0.35
    トウ
    0.35
    Activations Density 0.221%

    No Known Activations