© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3672
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms related to evidence and court proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    initialise
    -1.47
    Whilst
    -1.46
     Whilst
    -1.36
     enquiries
    -1.31
     realised
    -1.31
     organised
    -1.29
    Colour
    -1.27
     specialises
    -1.27
     whilst
    -1.26
     programme
    -1.25
    POSITIVE LOGITS
     confiable
    1.24
     neighborhoods
    1.23
     rumors
    1.23
     favorably
    1.22
    neighborhood
    1.22
     neighbors
    1.21
     harbors
    1.20
    Neighborhood
    1.20
    FAVOR
    1.20
     theaters
    1.19
    Activations Density 6.776%

    No Known Activations