© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11651
    Prev
    Next
    INDEX
    Explanations

    content related to rugby players and their accomplishments

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

    rugby or Ireland

    np_acts-logits-general · gemini-2.0-flash

    Ireland rugby union

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    väg
    -0.44
    nass
    -0.44
     Zenith
    -0.43
     garden
    -0.42
     shooting
    -0.41
    醐
    -0.41
     oil
    -0.41
    Mila
    -0.40
    Shooting
    -0.40
     driver
    -0.39
    POSITIVE LOGITS
     rugby
    0.93
    rugby
    0.86
     Rugby
    0.80
    🏉
    0.79
    Rugby
    0.73
     scrum
    0.62
     Premiership
    0.52
     Scrum
    0.50
    SequentialGroup
    0.45
     haka
    0.43
    Activations Density 0.094%

    No Known Activations