© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104761
    Prev
    Next
    INDEX
    Explanations

    words related to departures and takeoffs, particularly in an aviation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tranno
    -0.39
    tanleria
    -0.39
    enumi
    -0.38
    Спасылкі
    -0.38
     hű
    -0.36
    IsMutable
    -0.36
    DMETHOD
    -0.34
     ویکی‌پدی
    -0.34
     thing
    -0.33
    Erreferentziak
    -0.33
    POSITIVE LOGITS
     start
    0.83
     launch
    0.83
    launch
    0.79
     takeoff
    0.78
     Launch
    0.78
    start
    0.75
    Launch
    0.74
    PreExecute
    0.73
     Departure
    0.73
     Start
    0.72
    Activations Density 0.011%

    No Known Activations