© 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. 39-GEMMASCOPE-RES-16K
    11. 1772
    Prev
    Next
    INDEX
    Explanations

    phrases and notions associated with racial identity and historical injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    更好地
    -0.70
    こうした
    -0.69
    ごちそうさまでした
    -0.66
     “[
    -0.57
     offenbar
    -0.57
     "[
    -0.57
    Bises
    -0.56
     للاسماء
    -0.56
    RegressionTest
    -0.56
    “[
    -0.56
    POSITIVE LOGITS
    Thats
    1.23
     Thats
    1.20
    Lets
    1.13
    Its
    1.09
    Dont
    1.05
     thats
    1.04
    Whats
    1.04
     Lets
    1.00
     its
    0.98
    thats
    0.98
    Activations Density 0.592%

    No Known Activations