© 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. 33-GEMMASCOPE-RES-16K
    11. 8369
    Prev
    Next
    INDEX
    Explanations

    references to vintage cars and automotive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    عرِّف
    -0.38
    gensen
    -0.38
    Rhestr
    -0.38
    wnia
    -0.34
     reutiliz
    -0.34
     caminhada
    -0.33
    bių
    -0.33
    jścia
    -0.33
     interrom
    -0.33
     missione
    -0.33
    POSITIVE LOGITS
     vehicle
    1.73
     automobile
    1.71
     cars
    1.68
     car
    1.65
     automotive
    1.59
     Vehicle
    1.58
     vehicles
    1.55
     automobiles
    1.54
     driving
    1.51
    Vehicle
    1.51
    Activations Density 1.127%

    No Known Activations