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. 0-GEMMASCOPE-RES-16K
    6. 3378
    Prev
    Next
    INDEX
    Explanations

    information related to pregnancy and reproductive health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilanth
    -0.59
    มาะ
    -0.52
     Grom
    -0.51
    lück
    -0.48
    ssohn
    -0.48
    Clou
    -0.46
    子の
    -0.43
     trans
    -0.42
    показания
    -0.42
     myö
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.88
    PerformLayout
    0.86
    DockStyle
    0.83
    SpringBootTest
    0.82
     HasFactory
    0.82
     ویکی‌پدیا
    0.78
     pregnancy
    0.75
    Referencie
    0.75
     تضيفلها
    0.74
     initComponents
    0.74
    Activations Density 2.646%

    No Known Activations