© 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. 28-GEMMASCOPE-RES-16K
    11. 4646
    Prev
    Next
    INDEX
    Explanations

    terms related to public transportation systems, specifically metro stations

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

    German words about public transportation

    np_acts-logits-general · gemini-2.0-flash

    train stations and names

    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
     cheminée
    -0.45
    Chim
    -0.42
     Meksiku
    -0.40
    lccn
    -0.39
    ucción
    -0.39
    IndentedString
    -0.38
    toMatchSnapshot
    -0.38
     cæ
    -0.36
     fubject
    -0.36
     ftate
    -0.36
    POSITIVE LOGITS
     stations
    0.85
     subway
    0.82
     passengers
    0.81
     station
    0.79
     Passengers
    0.76
     Stations
    0.75
     commuters
    0.73
    Passengers
    0.70
     commuter
    0.70
     Station
    0.69
    Activations Density 0.181%

    No Known Activations