© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 57870
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lay" and its variations used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    operazione
    -0.95
    PRNewswire
    -0.93
    ufficio
    -0.85
     quæ
    -0.84
    centralwidget
    -0.84
     Escolar
    -0.82
    attenzione
    -0.82
     chré
    -0.80
    intervento
    -0.78
    effetto
    -0.77
    POSITIVE LOGITS
     Lay
    1.45
     LAY
    1.41
     lay
    1.35
    lay
    1.31
    Lay
    1.30
     laying
    1.23
     Laid
    1.20
     lays
    1.17
    laid
    1.16
     laid
    1.10
    Activations Density 0.009%

    No Known Activations