© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6902
    Prev
    Next
    INDEX
    Explanations

    names of players and their affiliations in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.69
    ViewImports
    -0.68
     nakalista
    -0.65
    ViewChild
    -0.64
     cherchés
    -0.64
     ddelweddau
    -0.63
    canActivate
    -0.62
    findpost
    -0.62
    ollectionView
    -0.61
     للمعارف
    -0.61
    POSITIVE LOGITS
     tweeted
    0.57
     teammate
    0.54
     dipin
    0.51
     teammates
    0.50
    mobileqq
    0.50
     serviceable
    0.49
    UrlResolution
    0.47
     scored
    0.46
     tweet
    0.46
    omitempty
    0.46
    Activations Density 0.150%

    No Known Activations