© 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. 23-GEMMASCOPE-RES-16K
    11. 11376
    Prev
    Next
    INDEX
    Explanations

    the word "lay" and its variations, indicating an emphasis on the concept of laying or placing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المكان
    -0.68
     cherchés
    -0.66
    ANDUM
    -0.62
     وتسجيلات
    -0.62
     المعيارى
    -0.61
    AsUp
    -0.60
     <<<<<<<<<<<<<<
    -0.60
     Paglinawan
    -0.58
     estimés
    -0.58
    MessageTagHelper
    -0.57
    POSITIVE LOGITS
     claim
    0.86
     laid
    0.84
    laid
    0.83
     fallow
    0.83
     lays
    0.81
     LAY
    0.79
     Laid
    0.79
     waste
    0.77
     dormant
    0.77
     siege
    0.74
    Activations Density 0.088%

    No Known Activations