© 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. 9796
    Prev
    Next
    INDEX
    Explanations

    technical terms or keywords related to programming or computational contexts

    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
     ſta
    -0.92
     houſe
    -0.90
     ſtate
    -0.88
     pleaſure
    -0.88
     ſte
    -0.86
     diſt
    -0.84
     ſever
    -0.84
     purpoſe
    -0.83
     paſſ
    -0.82
     deſt
    -0.82
    POSITIVE LOGITS
     שוליים
    0.70
    sements
    0.57
     Accumulation
    0.55
     امريكا
    0.55
     &___
    0.54
     resourceCulture
    0.54
    ẨM
    0.53
    kosh
    0.52
    inox
    0.51
    Weblinks
    0.51
    Activations Density 0.052%

    No Known Activations