© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8641
    Prev
    Next
    INDEX
    Explanations

    words related to motorsport events and drivers

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

    following numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    racing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esercit
    -0.52
     Betracht
    -0.51
     argint
    -0.50
     exercício
    -0.50
     Playhouse
    -0.50
    SharedCtor
    -0.48
    AlterField
    -0.48
    utnik
    -0.47
     végétale
    -0.47
     scolaire
    -0.47
    POSITIVE LOGITS
     race
    1.71
     racing
    1.67
     raced
    1.52
     racers
    1.51
     races
    1.50
     Racing
    1.49
     Race
    1.48
     racer
    1.47
    Racing
    1.46
    Race
    1.40
    Activations Density 0.251%

    No Known Activations