© 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. 21-GEMMASCOPE-RES-16K
    11. 5549
    Prev
    Next
    INDEX
    Explanations

    continuous use 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     térm
    -0.71
     feroit
    -0.69
     engraçadas
    -0.65
     Jefus
    -0.62
     inalámb
    -0.60
     recupero
    -0.60
     contratación
    -0.60
     auroit
    -0.60
    scribe
    -0.59
     urbanas
    -0.59
    POSITIVE LOGITS
     indeed
    0.85
     actually
    0.81
     also
    0.81
     CreateTagHelper
    0.75
     been
    0.74
     autorytatywna
    0.74
     certainly
    0.73
     always
    0.70
     not
    0.70
     put
    0.68
    Activations Density 0.289%

    No Known Activations