© 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. 0-GEMMASCOPE-RES-16K
    11. 15115
    Prev
    Next
    INDEX
    Explanations

    terms related to correspondence or relationships between variables or entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     juridiques
    -0.62
     nationaux
    -0.61
     chré
    -0.58
     européens
    -0.55
    AndFlush
    -0.55
    ethane
    -0.54
     internationaux
    -0.50
     rehearing
    -0.49
     solução
    -0.48
    ătoare
    -0.47
    POSITIVE LOGITS
     correspond
    1.96
    correspond
    1.87
     Correspond
    1.78
     corresponded
    1.74
     corresponds
    1.69
    Correspond
    1.68
     corrispond
    1.55
    corresponding
    1.53
     corresponding
    1.51
     correspon
    1.51
    Activations Density 0.140%

    No Known Activations