© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    references to female roles and relationships, particularly in the context of mating, motherhood, and domestic partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     self
    -0.51
     eget
    -0.50
     điển
    -0.48
    figer
    -0.46
    ník
    -0.46
    ianum
    -0.45
    ']").
    -0.44
    intree
    -0.44
    LookAnd
    -0.44
    étranger
    -0.42
    POSITIVE LOGITS
     herself
    0.73
    ResponseWriter
    0.72
     heiress
    0.63
     housewife
    0.62
    Diweddarwch
    0.59
    PerformLayout
    0.59
     Cupid
    0.59
    MultipartFile
    0.57
     female
    0.57
    herself
    0.57
    Activations Density 0.818%

    No Known Activations