© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-GEMMASCOPE-RES-16K
    11. 14493
    Prev
    Next
    INDEX
    Explanations

    phrases related to stability and reliability in systems or conditions

    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
    umbent
    -0.50
    nibal
    -0.48
    lop
    -0.46
    atory
    -0.45
     nose
    -0.45
     Cataloging
    -0.44
    oidal
    -0.44
    ستر
    -0.44
    फ्त
    -0.44
     Konk
    -0.44
    POSITIVE LOGITS
     surla
    0.65
    MigrationBuilder
    0.59
    RenderAtEndOf
    0.57
     slowest
    0.57
     ***!
    0.57
     ContentValues
    0.56
     aDecoder
    0.56
    RegressionTest
    0.56
    ThemeOverlay
    0.55
    tangentMode
    0.55
    Activations Density 0.594%

    No Known Activations