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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2558
    Prev
    Next
    INDEX
    Explanations

    terms related to automobiles and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.40
     relaj
    -0.39
    Chham
    -0.38
    новниш
    -0.38
     useState
    -0.38
    yarnpkg
    -0.37
     transición
    -0.37
     agujero
    -0.37
     StatefulWidget
    -0.37
     observación
    -0.37
    POSITIVE LOGITS
     vehicle
    2.11
     automobile
    2.03
     Vehicle
    1.95
    Vehicle
    1.95
     vehicles
    1.89
     cars
    1.89
    vehicle
    1.86
     automobiles
    1.84
     Jeep
    1.80
     automotive
    1.79
    Activations Density 0.713%

    No Known Activations