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. 10849
    Prev
    Next
    INDEX
    Explanations

    references to societal expectations surrounding parenthood and career choices

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

    Stereotypes and social norms

    np_acts-logits-general · gemini-2.0-flash

    social stereotypes and gender norms

    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
    Bronnen
    -0.71
     Roskov
    -0.71
     متعلقه
    -0.68
    TestingModule
    -0.65
    Begriffsklä
    -0.59
     intptr
    -0.58
    DockStyle
    -0.57
     nakalista
    -0.56
    RegistryLite
    -0.56
     estekak
    -0.55
    POSITIVE LOGITS
     stereotypes
    1.23
     stereotype
    1.15
     societal
    1.12
     stigma
    1.05
     stereotyp
    1.05
     assumptions
    1.00
     society
    1.00
     norms
    0.97
     stereotypical
    0.94
     Stere
    0.94
    Activations Density 0.437%

    No Known Activations