© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9148
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lay" and its variations in the context of laying or placing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.86
    centralwidget
    -0.83
    ufficio
    -0.81
    attenzione
    -0.80
    AndEndTag
    -0.79
     noblesse
    -0.79
    operazione
    -0.77
     Whal
    -0.77
    تفصیلات
    -0.77
    effetto
    -0.77
    POSITIVE LOGITS
     LAY
    1.24
     Lay
    1.23
     lay
    1.18
     laying
    1.12
    lay
    1.10
    Lay
    1.08
     lie
    1.08
     lying
    1.04
     Laid
    1.03
     Lies
    1.00
    Activations Density 0.087%

    No Known Activations