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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 820
    Prev
    Next
    INDEX
    Explanations

    concepts related to racial and ethnic representation in educational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     referenties
    -0.70
     تضيفلها
    -0.66
     privées
    -0.60
    脚注の使い方
    -0.58
    createServer
    -0.58
    InvalidProtocol
    -0.58
     présidenti
    -0.58
    Predecesor
    -0.57
    prepareStatement
    -0.57
    gouv
    -0.57
    POSITIVE LOGITS
     minorities
    1.52
     minority
    1.38
     African
    1.37
     ethnic
    1.30
     Hispanic
    1.21
     Asian
    1.20
    African
    1.15
     Asians
    1.10
     racial
    1.09
     Afro
    1.08
    Activations Density 0.483%

    No Known Activations