© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 14640
    Prev
    Next
    INDEX
    Explanations

    terms related to the ecology and characteristics of woodland areas

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     насељу
    -0.51
     rallado
    -0.50
     prefeitura
    -0.49
     ciudadano
    -0.48
     Chapin
    -0.46
     palmas
    -0.45
     EconPapers
    -0.45
     uș
    -0.45
     estekak
    -0.45
     muchacha
    -0.44
    POSITIVE LOGITS
     Shropshire
    0.55
     Dorset
    0.52
     countryside
    0.52
     Dart
    0.49
     Country
    0.48
     Devon
    0.48
     Rural
    0.48
    RSP
    0.47
     RSP
    0.46
     farmhouse
    0.46
    Activations Density 0.394%

    No Known Activations