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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11644
    Prev
    Next
    INDEX
    Explanations

    references to various types of vehicles, particularly buses and trucks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    aspectj
    -0.44
     BCC
    -0.38
    ellido
    -0.38
     Weiss
    -0.37
     Leiden
    -0.37
     Faul
    -0.37
     Leo
    -0.37
    Notae
    -0.36
    جغرافيا
    -0.36
     Bowen
    -0.35
    POSITIVE LOGITS
    Truck
    0.92
     Trucks
    0.91
     Truck
    0.91
     TRUCK
    0.89
     Buses
    0.85
     truck
    0.84
     trucks
    0.82
     buses
    0.79
     ainfi
    0.79
    truck
    0.74
    Activations Density 0.216%

    No Known Activations