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. 1998
    Prev
    Next
    INDEX
    Explanations

    references to ethnic identities and demographic groups in the context of sociopolitical issues

    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
    SequentialGroup
    -0.70
    MockBean
    -0.61
     الرياضيه
    -0.55
    KommentareTeilen
    -0.55
    AddTagHelper
    -0.50
     armature
    -0.50
    atiche
    -0.49
    出版年
    -0.48
    gypten
    -0.48
    hysema
    -0.47
    POSITIVE LOGITS
     ethnic
    1.21
     Ethnic
    1.03
    Ethnic
    1.00
     ethnicity
    1.00
     minorities
    0.98
    ethnic
    0.98
     racial
    0.96
     minority
    0.96
     étn
    0.93
     racially
    0.86
    Activations Density 0.488%

    No Known Activations