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. 20-GEMMASCOPE-RES-16K
    6. 4685
    Prev
    Next
    INDEX
    Explanations

    terms related to legal claims of discrimination and harassment

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

    Terms related to discrimination or harassment

    np_acts-logits-general · gemini-2.0-flash

    sexual discrimination and harassment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Comté
    -0.53
    ÉM
    -0.49
    fromnode
    -0.48
    ரி
    -0.48
    lampa
    -0.46
    最快更新
    -0.45
    ழ்
    -0.45
    bef
    -0.44
    حياته
    -0.44
     bef
    -0.44
    POSITIVE LOGITS
     discrimination
    0.97
     Discrimination
    0.97
    discrimination
    0.87
     discriminated
    0.83
     EconPapers
    0.83
     Discrimin
    0.82
     Equal
    0.82
     Harassment
    0.77
    Equal
    0.77
     discrimin
    0.76
    Activations Density 0.484%

    No Known Activations