© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    discourse markers indicating contrast or exception

    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
    generally
    -0.63
     btw
    -0.60
     Generally
    -0.59
     generally
    -0.58
    definitely
    -0.57
    Generally
    -0.56
     lastly
    -0.55
     Definitely
    -0.55
     generell
    -0.54
     definitely
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.79
    SequentialGroup
    0.59
    Cyfeiriadau
    0.53
    rawDesc
    0.52
     woorden
    0.51
     geschiedenis
    0.51
     semejante
    0.50
     Erwartungen
    0.49
     financeira
    0.48
     décadas
    0.47
    Activations Density 0.480%

    No Known Activations