© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9478
    Prev
    Next
    INDEX
    Explanations

    years or seasons related to sports achievements or events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    úrese
    -0.46
     Lifeline
    -0.43
     wider
    -0.42
    ニーカー
    -0.42
     Bowie
    -0.42
     tá
    -0.40
    ็จ
    -0.38
    setTimeout
    -0.38
     mesure
    -0.37
     state
    -0.37
    POSITIVE LOGITS
    LookAnd
    1.23
     Monfieur
    1.02
     Efq
    1.02
     myſelf
    1.01
    oredCriteria
    0.99
     Theſe
    0.99
     themſelves
    0.98
    Datuak
    0.96
     himſelf
    0.95
     itſelf
    0.89
    Activations Density 0.146%

    No Known Activations