© 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. 37-GEMMASCOPE-RES-16K
    11. 3603
    Prev
    Next
    INDEX
    Explanations

    sentences related to discussions of historical context and obligation regarding slavery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.57
     defaultstate
    -0.46
     >=",
    -0.46
     ***!
    -0.44
    #+#
    -0.44
    andExpect
    -0.43
    invokeLater
    -0.41
    原始内容存档于
    -0.40
    forChild
    -0.40
     насељу
    -0.40
    POSITIVE LOGITS
     would
    3.63
    would
    2.75
     Would
    2.63
    Would
    2.61
     WOULD
    2.31
     würde
    1.99
     sería
    1.89
     serait
    1.87
     wouldn
    1.86
     würden
    1.86
    Activations Density 2.595%

    No Known Activations