© 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. 34-GEMMASCOPE-RES-16K
    11. 3379
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal and judicial processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    gäng
    -0.52
    InputTagHelper
    -0.44
    XmlType
    -0.42
     vVar
    -0.42
    諷
    -0.42
    akhstan
    -0.41
    UCN
    -0.41
    .*")]
    -0.39
    ronpa
    -0.39
    witzerland
    -0.39
    POSITIVE LOGITS
     auquel
    1.09
     auxquels
    1.01
     auxquelles
    0.98
     upon
    0.94
    Into
    0.89
     waarmee
    0.87
     waarop
    0.86
    Upon
    0.86
     into
    0.84
     whom
    0.82
    Activations Density 0.742%

    No Known Activations