© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31843
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repeated statements or announcements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    said before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.78
    TintMode
    -0.63
    ########.
    -0.56
    IBarButtonItem
    -0.56
    FormTagHelper
    -0.52
    StructEnd
    -0.52
     grà
    -0.52
    GEBURTSDATUM
    -0.51
     AssemblyCompany
    -0.50
    initComponents
    -0.50
    POSITIVE LOGITS
     myſelf
    0.84
     ſaid
    0.81
     reaſon
    0.73
     miſ
    0.72
     pleaſure
    0.72
     ſhould
    0.71
     beſt
    0.71
     cauſe
    0.70
     ſtate
    0.70
     houſe
    0.70
    Activations Density 0.069%

    No Known Activations