Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75496
    Prev
    Next
    INDEX
    Explanations

    references to machinery and heavy equipment in various contexts

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

    heavy machinery and vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     OFDb
    -0.52
     initComponents
    -0.49
    hyrchwyd
    -0.48
    rawDesc
    -0.48
    drage
    -0.43
    пиона
    -0.43
    дарь
    -0.42
    uerre
    -0.42
    FunctionFlags
    -0.42
     littéraire
    -0.42
    POSITIVE LOGITS
     tractor
    0.73
     tractors
    0.73
     excavator
    0.69
     excav
    0.60
     Tractor
    0.58
    dozer
    0.57
     machines
    0.56
     truck
    0.55
    🚜
    0.54
     forklift
    0.52
    Activations Density 0.009%

    No Known Activations