© 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. 25-GEMMASCOPE-RES-16K
    11. 11402
    Prev
    Next
    INDEX
    Explanations

    diverse character representations and sequences, often related to formal structures or categories in text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     --
    -0.55
     doesnt
    -0.44
     didnt
    -0.44
    "--
    -0.43
    ****************
    -0.42
     wasnt
    -0.42
    "....
    -0.42
     ----
    -0.40
     childrens
    -0.40
     isnt
    -0.40
    POSITIVE LOGITS
     Ō
    0.73
     Māori
    0.73
     
    0.72
     résumé
    0.71
     α
    0.69
     β
    0.69
     Mā
    0.68
     cafés
    0.66
     θ
    0.66
     Kō
    0.65
    Activations Density 35.097%

    No Known Activations