© 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. 20-GEMMASCOPE-RES-16K
    11. 3484
    Prev
    Next
    INDEX
    Explanations

    features related to vehicle specifications and unique design elements

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

    Car models after "new" or "the"

    np_acts-logits-general · gemini-2.0-flash

    SUV, crossover, and car models

    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
     consultato
    -0.63
    WindowConstants
    -0.57
    CodedInputStream
    -0.56
     toer
    -0.49
     OMITBAD
    -0.49
    clyde
    -0.48
    וויק
    -0.47
     DDT
    -0.46
    oprecip
    -0.45
    FieldNumber
    -0.45
    POSITIVE LOGITS
     SUV
    0.92
    SUV
    0.81
     SUVs
    0.72
     suv
    0.72
     crossover
    0.67
    AnchorStyles
    0.61
     hybrid
    0.59
    crossover
    0.59
    uride
    0.57
    ///</
    0.56
    Activations Density 0.148%

    No Known Activations