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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112520
    Prev
    Next
    INDEX
    Explanations

    mentions of social injustices and discrimination experienced by marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    racism, sexism, discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     navideñas
    -0.48
     otomatig
    -0.46
     proprement
    -0.45
     deportivas
    -0.45
     stället
    -0.44
     AssemblyVersion
    -0.43
     незавершена
    -0.42
     informée
    -0.41
     disegni
    -0.39
     matrícula
    -0.39
    POSITIVE LOGITS
    ah
    0.48
    borderSide
    0.47
     discrimination
    0.45
     sexism
    0.45
     racism
    0.44
     persecution
    0.44
     unfair
    0.44
    ism
    0.44
     Racism
    0.44
    discrimination
    0.43
    Activations Density 0.038%

    No Known Activations