© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5774
    Prev
    Next
    INDEX
    Explanations

    references to discrimination and social justice issues

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

    Legal and civil rights contexts involving race

    np_acts-logits-general · gemini-2.0-flash

    racial justice and legal acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    featureID
    -0.64
     تضيفلها
    -0.58
    TestBed
    -0.58
    TagMode
    -0.57
     _$
    -0.57
    enterOuterAlt
    -0.55
    sizeCache
    -0.55
     FishBase
    -0.55
    complexContent
    -0.55
    styleUrls
    -0.55
    POSITIVE LOGITS
     racial
    1.87
     racism
    1.82
     racist
    1.73
     Racial
    1.65
     racially
    1.63
     Racism
    1.56
     Diversity
    1.49
    Racism
    1.48
    racial
    1.47
     diversity
    1.45
    Activations Density 0.769%

    No Known Activations