© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7362
    Prev
    Next
    INDEX
    Explanations

    elements related to vehicles and automobile features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.48
     referenties
    -0.41
    rungsseite
    -0.39
     Reised
    -0.36
     Tapia
    -0.35
     hierba
    -0.35
     piernas
    -0.34
     povin
    -0.34
     Espinoza
    -0.34
     macetas
    -0.34
    POSITIVE LOGITS
     Ford
    1.72
     Toyota
    1.69
     BMW
    1.68
     Nissan
    1.66
     Mercedes
    1.64
     Honda
    1.64
     Audi
    1.60
     Volkswagen
    1.59
     Mazda
    1.55
     VW
    1.52
    Activations Density 0.600%

    No Known Activations