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. 7287
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to health risks and reproductive age factors

    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
     madam
    -0.95
     actress
    -0.94
     actresses
    -0.93
     lady
    -0.91
     Lady
    -0.91
    Madam
    -0.88
     Actress
    -0.88
     Madam
    -0.88
     goddess
    -0.88
     LADY
    -0.86
    POSITIVE LOGITS
     male
    1.18
     masculine
    1.17
     masculinity
    1.17
     manly
    1.14
     pria
    1.14
     gentlemen
    1.09
     masculino
    1.09
     masculina
    1.07
     manhood
    1.07
     Mascul
    1.06
    Activations Density 0.572%

    No Known Activations