© 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. 3-GEMMASCOPE-RES-16K
    11. 4517
    Prev
    Next
    INDEX
    Explanations

    forms of the verbs "have" and "has"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.83
     Seeder
    -0.79
    DataAnnotations
    -0.77
     EdgeInsets
    -0.72
    SequentialGroup
    -0.72
     NavController
    -0.69
     utafitiHapana
    -0.68
     født
    -0.68
     faſt
    -0.68
    windowFixed
    -0.68
    POSITIVE LOGITS
     has
    0.70
     always
    0.60
     will
    0.60
     consistently
    0.59
     are
    0.58
     currently
    0.56
     hiện
    0.50
     often
    0.50
     have
    0.50
     usually
    0.49
    Activations Density 0.237%

    No Known Activations