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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8071
    Prev
    Next
    INDEX
    Explanations

    terms related to the Olympics and Olympic events

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

    the Olympic Games

    np_acts-logits-general · gemini-2.0-flash

    Olympic Games and Summer Olympics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.67
     CreateTagHelper
    -0.65
    mybatisplus
    -0.65
     AssemblyCulture
    -0.63
    posedge
    -0.57
    apunov
    -0.57
    ungeon
    -0.56
     Baillargeon
    -0.55
    PerformLayout
    -0.54
    وفاته
    -0.53
    POSITIVE LOGITS
     Games
    1.41
    Games
    1.23
     games
    1.18
     Olympics
    1.12
     GAMES
    1.06
    games
    1.06
     Olympic
    1.00
    GAMES
    0.94
     Spiele
    0.88
     juegos
    0.85
    Activations Density 0.068%

    No Known Activations