© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    numeric values or references to quantities and percentages

    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
     personal
    -0.56
     construction
    -0.53
     Vle
    -0.52
     
    -0.52
    ள்
    -0.52
     tomo
    -0.50
     contrat
    -0.49
    λοι
    -0.49
     constr
    -0.49
                                   
    -0.48
    POSITIVE LOGITS
    9
    1.21
     Ninth
    1.03
     ninety
    1.02
     Ninety
    0.99
    Datuak
    0.97
     Nine
    0.95
    Nine
    0.94
    nine
    0.92
     九
    0.92
    ⁹
    0.90
    Activations Density 0.203%

    No Known Activations