© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    references to stereotypes, particularly those related to Native Americans

    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
    AnchorTagHelper
    -0.44
     bağlantılar
    -0.40
    RTLU
    -0.39
    дарю
    -0.38
    \{\\
    -0.38
    digkeit
    -0.36
    loài
    -0.36
     pleaſure
    -0.36
    Jereo
    -0.36
     pray
    -0.35
    POSITIVE LOGITS
     stereotypes
    1.61
     misconceptions
    1.52
     precon
    1.45
     stereotype
    1.43
     misconception
    1.34
     prejudices
    1.30
     myths
    1.29
     perceptions
    1.27
     stigma
    1.23
     perception
    1.20
    Activations Density 0.637%

    No Known Activations