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. 20-GEMMASCOPE-RES-16K
    6. 5146
    Prev
    Next
    INDEX
    Explanations

    information about airports and their associated statistics

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

    airports

    np_acts-logits-general · gemini-2.0-flash

    airports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.72
     CreateTagHelper
    -0.59
    //
    -0.57
     propOrder
    -0.53
     autorytatywna
    -0.50
    ngdoc
    -0.49
    pect
    -0.48
    WarningLevel
    -0.48
     محفوظة
    -0.47
     كورة
    -0.46
    POSITIVE LOGITS
     airport
    1.55
     airports
    1.42
     Airport
    1.34
    airport
    1.27
     aeropuerto
    1.25
     aeroporto
    1.21
     Airports
    1.20
    Airport
    1.19
     Flughafen
    1.08
     Aeropuerto
    1.05
    Activations Density 0.119%

    No Known Activations