© 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. 8907
    Prev
    Next
    INDEX
    Explanations

    numerical data related to income statistics

    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
     endeavour
    -0.65
     rumours
    -0.62
     flavour
    -0.61
    initialise
    -0.59
     rumour
    -0.58
     rumoured
    -0.58
     endeavouring
    -0.58
     flavours
    -0.57
     ModelExpression
    -0.57
     colourful
    -0.56
    POSITIVE LOGITS
     Hispanic
    0.71
     statewide
    0.69
     Census
    0.69
     Hispanics
    0.66
     counties
    0.66
     ZIP
    0.63
    Hispanic
    0.62
     Americans
    0.59
     metro
    0.59
     nationwide
    0.59
    Activations Density 0.672%

    No Known Activations