© 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. 22-GEMMASCOPE-RES-16K
    11. 3833
    Prev
    Next
    INDEX
    Explanations

    references to vehicles and their actions within various contexts

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

    motor vehicles

    np_acts-logits-general · gemini-2.0-flash

    vehicles associated with possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.52
    HandlerContext
    -0.46
    OCCURRED
    -0.46
     ovate
    -0.46
     Процитовано
    -0.45
    tite
    -0.45
    genen
    -0.45
     puertos
    -0.45
    printStackTrace
    -0.44
     белье
    -0.44
    POSITIVE LOGITS
     cars
    1.68
     vehicles
    1.60
     vehicle
    1.57
     car
    1.54
    vehicle
    1.32
     automobiles
    1.32
     Vehicles
    1.28
     automobile
    1.22
     jeep
    1.22
     SUV
    1.21
    Activations Density 0.387%

    No Known Activations