© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7951
    Prev
    Next
    INDEX
    Explanations

    references to vehicles, specifically golf carts and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dữ
    -0.39
     ffilm
    -0.38
     TextAlign
    -0.38
    Personendaten
    -0.37
    ILabel
    -0.37
    ClientRect
    -0.36
    GeneratedValue
    -0.35
    rungsseite
    -0.35
    *{\
    -0.35
    SqlClient
    -0.35
    POSITIVE LOGITS
     scooter
    1.20
     scooters
    1.10
    scooter
    1.04
     Scooter
    1.04
    Scooter
    0.91
     Sco
    0.77
     motorized
    0.76
     Vespa
    0.75
     tricycle
    0.73
     ATV
    0.72
    Activations Density 0.153%

    No Known Activations