© 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. 9-GEMMASCOPE-RES-16K
    11. 955
    Prev
    Next
    INDEX
    Explanations

    dates and temporal references associated with events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.73
     Theſe
    -0.72
     itſelf
    -0.71
     nahilalakip
    -0.68
     Reſ
    -0.66
     समीक्षाओं
    -0.66
    ItemBackground
    -0.66
     Cæsar
    -0.66
    存于互联网档案馆
    -0.66
    LLocation
    -0.65
    POSITIVE LOGITS
    SequentialGroup
    0.74
     when
    0.67
    давно
    0.62
     recently
    0.61
    När
    0.61
     ago
    0.57
     Mur
    0.55
    ついに
    0.55
     When
    0.54
     Bal
    0.54
    Activations Density 0.411%

    No Known Activations