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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9900
    Prev
    Next
    INDEX
    Explanations

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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.60
    yttö
    -0.44
    ništvo
    -0.42
     kartą
    -0.40
    enschutz
    -0.39
    ☚
    -0.39
     Offisielt
    -0.39
    uação
    -0.39
     لیتر
    -0.38
     poveznice
    -0.38
    POSITIVE LOGITS
     lay
    1.69
     Lay
    1.63
     laying
    1.58
     laid
    1.44
    Lay
    1.41
     lays
    1.40
     LAY
    1.38
    laying
    1.35
     Laid
    1.23
     layouts
    1.18
    Activations Density 1.742%

    No Known Activations