© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10783
    Prev
    Next
    INDEX
    Explanations

    mentions of sports and related terminology

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

    "sports" appearing at the start of phrases

    np_acts-logits-general · gemini-2.0-flash

    sports and associates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huesos
    -0.43
     témoins
    -0.39
     cielos
    -0.39
     obreros
    -0.39
     Shee
    -0.38
     bolsillos
    -0.37
     ממש
    -0.37
     mempel
    -0.36
     chapters
    -0.36
    VersionUID
    -0.36
    POSITIVE LOGITS
    httphttps
    0.66
    delwed
    0.63
    webElementXpaths
    0.60
     BrowserModule
    0.54
    Sports
    0.54
    featureID
    0.54
    GenerationType
    0.53
    UserScript
    0.53
     Sport
    0.53
    Personensuche
    0.52
    Activations Density 0.113%

    No Known Activations