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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4774
    Prev
    Next
    INDEX
    Explanations

    terms related to gender dynamics and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     estekak
    -1.06
     linkovi
    -0.90
    ISupport
    -0.87
     насељу
    -0.86
    CppCodeGen
    -0.84
     getItemId
    -0.81
     defaultstate
    -0.80
     gainera
    -0.76
     ControllerBase
    -0.76
     ddelweddau
    -0.76
    POSITIVE LOGITS
     disparity
    0.57
     differences
    0.56
     equality
    0.56
     роли
    0.56
    ed
    0.56
     roles
    0.55
     balance
    0.51
     gap
    0.50
     لينك
    0.49
     ratios
    0.48
    Activations Density 0.092%

    No Known Activations