© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 157
    Prev
    Next
    INDEX
    Explanations

    verbs associated with laying down or placing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "lay" (laid, lays, laying)

    np_acts-logits-general · gemini-2.0-flash

    lay + phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.07
    脚注の使い方
    -0.83
    SharedDtor
    -0.77
     estimés
    -0.74
     <<<<<<<<<<<<<<
    -0.74
    
    -0.72
     وتسجيلات
    -0.70
    رشف
    -0.66
     nakalista
    -0.65
    ArrowToggle
    -0.64
    POSITIVE LOGITS
     lay
    0.94
     Lay
    0.92
     lays
    0.90
    lay
    0.89
     LAY
    0.89
    Lay
    0.87
     laid
    0.87
     laying
    0.86
    lays
    0.83
    laid
    0.78
    Activations Density 0.055%

    No Known Activations