© 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. 37-GEMMASCOPE-RES-16K
    11. 9082
    Prev
    Next
    INDEX
    Explanations

    descriptions of personality types and social behavior

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    已然
    -0.95
     iż
    -0.94
     requisite
    -0.90
     således
    -0.90
    这般
    -0.88
    に於
    -0.86
     Subsequently
    -0.84
    でございます
    -0.82
    sidemargin
    -0.81
     medesimo
    -0.81
    POSITIVE LOGITS
     lots
    0.72
     really
    0.65
    Lots
    0.64
     things
    0.62
     żeby
    0.60
     different
    0.59
     разных
    0.57
     everybody
    0.56
     bigger
    0.56
     kinds
    0.56
    Activations Density 2.785%

    No Known Activations