© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13215
    Prev
    Next
    INDEX
    Explanations

    phrases related to athletic competitions, particularly combat sports

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

    Boxing and mixed martial arts

    np_acts-logits-general · gemini-2.0-flash

    combat sports rounds and outcomes

    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
    -0.62
    parsedMessage
    -0.60
    jspx
    -0.57
    addGroup
    -0.57
     المعيارى
    -0.56
    :]:
    -0.54
     EconPapers
    -0.54
     Reader
    -0.53
    ingeki
    -0.53
    SharedCtor
    -0.52
    POSITIVE LOGITS
     boxing
    1.03
     Boxing
    0.86
     boxer
    0.84
     boxers
    0.79
    🥊
    0.78
    Boxing
    0.78
     boks
    0.75
     boxe
    0.74
    boxing
    0.71
     ring
    0.69
    Activations Density 0.089%

    No Known Activations