© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11610
    Prev
    Next
    INDEX
    Explanations

    references to championships and related titles in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Luk
    -0.62
     gre
    -0.60
    cas
    -0.53
    tik
    -0.53
     Dus
    -0.52
    Agra
    -0.52
    hoots
    -0.52
    bag
    -0.51
     SENT
    -0.50
    gouv
    -0.50
    POSITIVE LOGITS
     Championship
    2.80
     championship
    2.74
    Championship
    2.49
     championships
    2.42
     Championships
    2.29
    champions
    2.02
     CHAMPION
    1.82
     campeonato
    1.60
     champions
    1.51
     championnat
    1.44
    Activations Density 0.042%

    No Known Activations