© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 15076
    Prev
    Next
    INDEX
    Explanations

    references to Jewish people and related terms that may indicate stereotypes or negative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.44
     paraître
    -0.44
    itoare
    -0.39
     AppColors
    -0.38
    InputBorder
    -0.37
     szól
    -0.36
     jScrollPane
    -0.35
     Unterscheidung
    -0.35
    rungsseite
    -0.35
    composición
    -0.35
    POSITIVE LOGITS
     Jewish
    0.69
     Jews
    0.69
     Jew
    0.69
    Jewish
    0.68
     Hebrew
    0.64
    Jews
    0.63
     jewish
    0.62
     Judaism
    0.61
     Tear
    0.60
    Datuak
    0.60
    Activations Density 1.899%

    No Known Activations