Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 426
    Prev
    Next
    INDEX
    Explanations

    references to diversity and representation of marginalized groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to racial and gender diversity, marginalized groups, and social representation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.48
    machinery
    -0.46
    WriteTagHelper
    -0.45
     okaza
    -0.42
    
    -0.41
    equipment
    -0.41
     verw
    -0.39
     nią
    -0.39
     zuk
    -0.38
     Outputs
    -0.38
    POSITIVE LOGITS
     minorities
    0.85
     racial
    0.81
     racism
    0.79
     racist
    0.77
     ethnic
    0.72
     Ethnic
    0.65
     racially
    0.65
     Racism
    0.64
     ethnicity
    0.64
     Racial
    0.63
    Activations Density 0.294%

    No Known Activations