© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4099
    Prev
    Next
    INDEX
    Explanations

    references to buses and related terminology in various contexts

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

    "Bus" or "Plane"

    np_acts-logits-general · gemini-2.0-flash

    Bushell, bus, plane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genética
    -0.41
     apellidos
    -0.36
     encaje
    -0.35
     repuesto
    -0.34
     EQUAL
    -0.34
     Naciones
    -0.33
     Román
    -0.33
     ponta
    -0.32
    Saldo
    -0.32
     ciudadana
    -0.32
    POSITIVE LOGITS
     Bus
    0.79
     bus
    0.77
     BUS
    0.70
    Bus
    0.69
     buses
    0.68
     Plane
    0.68
     Planes
    0.66
    \{\\
    0.65
    Buses
    0.64
     plane
    0.63
    Activations Density 0.161%

    No Known Activations