© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9957
    Prev
    Next
    INDEX
    Explanations

    references to race and demographic identities, particularly concerning white individuals and audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.63
    mybatisplus
    -0.61
     صوتيه
    -0.60
     FBref
    -0.55
     تضيفلها
    -0.52
     الرياضيه
    -0.52
     Chwiliwch
    -0.49
    JNIEnv
    -0.48
    engarkan
    -0.47
     Chop
    -0.45
    POSITIVE LOGITS
     Western
    0.46
     Europeans
    0.46
     European
    0.45
    西方
    0.45
     europe
    0.43
     caucasian
    0.41
     Europe
    0.41
     white
    0.41
     western
    0.41
     Anglo
    0.41
    Activations Density 0.245%

    No Known Activations