© 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. 5216
    Prev
    Next
    INDEX
    Explanations

    references to options or choices within a context, particularly related to menus or selections

    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
    BeginContext
    -1.00
    BagLayout
    -0.98
    PerformLayout
    -0.94
    ymas
    -0.92
    eryllium
    -0.90
    hematical
    -0.89
     BIBSYS
    -0.89
    >");
    -0.88
    Tembelea
    -0.85
    createServer
    -0.84
    POSITIVE LOGITS
     options
    1.86
     option
    1.75
     Options
    1.73
    options
    1.66
     Option
    1.60
     OPTION
    1.59
    Options
    1.58
    option
    1.53
    Option
    1.50
     OPTIONS
    1.48
    Activations Density 0.063%

    No Known Activations