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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10443
    Prev
    Next
    INDEX
    Explanations

    references to participants and events in the Olympics, particularly focusing on athletes and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apunov
    -0.58
    tvguidetime
    -0.55
    êques
    -0.53
    oa̍t
    -0.51
     Dott
    -0.50
    mybatisplus
    -0.50
    Constantes
    -0.49
    chyma
    -0.47
    bewerken
    -0.47
    InSection
    -0.47
    POSITIVE LOGITS
     Games
    1.42
     games
    1.25
    Games
    1.23
     Olympics
    1.16
    games
    1.13
     Olympic
    1.12
     GAMES
    1.08
     juegos
    0.97
    GAMES
    0.96
     Juegos
    0.92
    Activations Density 0.080%

    No Known Activations