© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 375
    Prev
    Next
    INDEX
    Explanations

    descriptions of thrilling experiences or adventures

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

    descriptive language related to thrilling experiences or adventures

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

    ride or drive

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ErrIntOverflow
    -0.57
    IUrlHelper
    -0.53
    SizeF
    -0.53
     nawr
    -0.52
    GEBURTSDATUM
    -0.50
    findpost
    -0.49
    ایز
    -0.49
     كومونز
    -0.48
    ंदीखरीदारी
    -0.47
    vetti
    -0.47
    POSITIVE LOGITS
     ride
    1.48
     rides
    1.15
    ride
    1.12
     Ride
    1.05
     RIDE
    1.05
    Ride
    1.04
     Rides
    0.92
     ridden
    0.91
    rides
    0.90
     rode
    0.84
    Activations Density 0.092%

    No Known Activations