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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 903
    Prev
    Next
    INDEX
    Explanations

    references to gender-related issues and women's representation and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.64
     وتسجيلات
    -0.61
    CppMethod
    -0.59
    ircraft
    -0.55
    enterOuterAlt
    -0.55
    IVEREF
    -0.54
     للاسماء
    -0.54
    ÁN
    -0.53
    Tuber
    -0.53
    idosis
    -0.53
    POSITIVE LOGITS
     female
    1.17
     Women
    1.16
     Female
    1.16
     women
    1.15
    Female
    1.15
    female
    1.14
    Women
    1.13
     fémin
    1.13
     feminine
    1.10
     féminine
    1.09
    Activations Density 0.399%

    No Known Activations