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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105957
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic status and related disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dium
    -0.40
    Hentet
    -0.40
    \",\
    -0.40
    phism
    -0.39
    contentLoaded
    -0.39
    Bibliograf
    -0.39
     forthwith
    -0.38
    ásticas
    -0.38
     đu
    -0.38
     
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    0.57
    Personensuche
    0.54
    RegressionTest
    0.50
    borderSide
    0.47
     smartest
    0.45
     régionales
    0.42
    XmlIgnore
    0.40
     noDo
    0.40
     NSCoder
    0.40
    
    0.39
    Activations Density 0.032%

    No Known Activations