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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2081
    Prev
    Next
    INDEX
    Explanations

    words related to vehicles, specifically "car."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tiefen
    -0.96
    BibitemShut
    -0.88
    Tikang
    -0.84
     ſeveral
    -0.82
     reaſon
    -0.79
     pleaſure
    -0.79
    )");
    -0.79
     myſelf
    -0.78
    )";
    -0.76
     Theſe
    -0.75
    POSITIVE LOGITS
     car
    2.97
     cars
    2.61
    car
    2.39
     Car
    2.37
    Car
    2.30
     Cars
    2.28
    cars
    2.22
    Cars
    2.19
     CAR
    1.91
     CARS
    1.88
    Activations Density 0.032%

    No Known Activations