© 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. 40-GEMMASCOPE-RES-16K
    11. 8639
    Prev
    Next
    INDEX
    Explanations

    comparisons and phrases that emphasize maximizing efficiency or potential

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Possibility
    -1.20
    possibility
    -1.18
    Possibility
    -1.17
     possibilidade
    -1.05
     Possibilities
    -1.01
     posibilidad
    -0.99
    Potential
    -0.97
     possibility
    -0.96
     Potential
    -0.88
     posibilidades
    -0.87
    POSITIVE LOGITS
     practically
    0.65
     physically
    0.60
     technologically
    0.56
     absolutely
    0.54
     reasonably
    0.53
     technically
    0.53
     human
    0.52
     pos
    0.49
     medically
    0.47
     legally
    0.47
    Activations Density 0.253%

    No Known Activations