© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4578
    Prev
    Next
    INDEX
    Explanations

    references to the working class and socio-economic class distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -0.38
      
    -0.38
     
    -0.35
     Cop
    -0.34
     private
    -0.33
     blowing
    -0.33
     BLO
    -0.32
     contract
    -0.31
     style
    -0.31
     super
    -0.31
    POSITIVE LOGITS
     estekak
    0.84
    脚注の使い方
    0.81
    enderror
    0.80
    AISSEE
    0.78
     ExecuteAsync
    0.75
    webElementXpaths
    0.73
    rungsseite
    0.72
    parsedMessage
    0.72
    tagHelperRunner
    0.71
    Personensuche
    0.71
    Activations Density 2.460%

    No Known Activations