© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2725
    Prev
    Next
    INDEX
    Explanations

    references to racial demographics and issues related to social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vereinbarung
    -0.38
    since
    -0.38
     abraço
    -0.38
     zakład
    -0.38
     outputs
    -0.37
     provisoire
    -0.37
     giriş
    -0.37
    رشف
    -0.37
     McNamara
    -0.36
     vuelo
    -0.36
    POSITIVE LOGITS
     minorities
    0.62
     Jews
    0.61
     ujednoznacz
    0.57
    
    0.57
     racial
    0.54
     Blacks
    0.51
     Hispanics
    0.51
    sidemargin
    0.51
     Racial
    0.50
     racism
    0.50
    Activations Density 0.606%

    No Known Activations