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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 73740
    Prev
    Next
    INDEX
    Explanations

    technical references to sensors and controllers in a quadcopter 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
    contentLoaded
    -0.76
     ब्रेकडाउन
    -0.63
     scattata
    -0.54
    IsMutable
    -0.53
     transfieras
    -0.51
    niająca
    -0.51
    ंदीखरीदारी
    -0.50
    writeFieldEnd
    -0.50
    rdı
    -0.47
    Diweddarwch
    -0.47
    POSITIVE LOGITS
     drone
    0.50
     Drone
    0.48
     autopilot
    0.47
    SupportActionBar
    0.45
     Drones
    0.44
     Integr
    0.43
     DJI
    0.42
     drones
    0.40
    
    0.40
     dji
    0.39
    Activations Density 0.014%

    No Known Activations