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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9624
    Prev
    Next
    INDEX
    Explanations

    terms related to the characteristics and behavior of prehistoric reptiles, specifically crocodilians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyCulture
    -0.71
     itſelf
    -0.67
    AddTagHelper
    -0.63
     myſelf
    -0.62
     IMEI
    -0.62
     opium
    -0.62
     isomer
    -0.61
    esgue
    -0.60
    ollectionView
    -0.60
     Huguen
    -0.60
    POSITIVE LOGITS
     Dinosaur
    0.98
     dinosaur
    0.97
    Dinosaur
    0.93
    🦖
    0.92
    dinosaur
    0.88
     dinosaurios
    0.86
     Dinosaurs
    0.85
     dinosaurs
    0.84
     dinoss
    0.82
     dinosau
    0.81
    Activations Density 0.203%

    No Known Activations