© 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. 18-GEMMASCOPE-RES-16K
    11. 10345
    Prev
    Next
    INDEX
    Explanations

    objects or entities related to sports and competition

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

    stadiums and arenas

    np_acts-logits-general · gemini-2.0-flash

    stadiums and venues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.69
    帖最后由
    -0.59
    EDEFAULT
    -0.57
    IconModule
    -0.57
    parsedMessage
    -0.55
    спеди
    -0.53
    tagHelperRunner
    -0.53
     الحره
    -0.52
    MigrationBuilder
    -0.52
     resourceCulture
    -0.51
    POSITIVE LOGITS
     stadium
    1.21
     stadiums
    1.08
     Stadium
    1.02
     venue
    0.96
    stadium
    0.92
    Stadium
    0.91
     estadio
    0.90
     stadion
    0.90
     venues
    0.87
     arena
    0.82
    Activations Density 0.134%

    No Known Activations