Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9112
    Prev
    Next
    INDEX
    Explanations

    references to airport and airline activities or contexts

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

    airports

    np_acts-logits-general · gemini-2.0-flash

    airport and travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PyLong
    -0.69
     Himo
    -0.65
    ValueStyle
    -0.60
    يميديا
    -0.58
    SuppressLint
    -0.56
    Hydro
    -0.55
    InjectAttribute
    -0.54
    //});
    -0.53
     Silurian
    -0.52
    dams
    -0.52
    POSITIVE LOGITS
     airport
    1.14
     Airport
    0.99
     Flughafen
    0.90
     airports
    0.89
     Terminal
    0.88
    airport
    0.85
    Airport
    0.83
     airline
    0.83
     luggage
    0.82
     Airlines
    0.81
    Activations Density 0.184%

    No Known Activations