© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15047
    Prev
    Next
    INDEX
    Explanations

    references to racial and ethnic heritage or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.59
    itaries
    -0.59
    исленность
    -0.58
    Vidite
    -0.56
    addCriterion
    -0.53
    ⓧ
    -0.52
    copg
    -0.52
    +#+#
    -0.51
    ngdoc
    -0.50
    __":
    
    -0.49
    POSITIVE LOGITS
     heritage
    0.59
     ancestry
    0.54
    heritage
    0.52
    Nationalité
    0.47
     Heritage
    0.45
     ethnicity
    0.43
    Heritage
    0.42
     Ancestry
    0.41
     pochod
    0.41
     inheritance
    0.41
    Activations Density 0.576%

    No Known Activations