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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122675
    Prev
    Next
    INDEX
    Explanations

    references to pregnancy and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     للاسماء
    -0.53
     Italijanski
    -0.53
    achios
    -0.50
    omials
    -0.50
    ugian
    -0.49
    lusconi
    -0.49
     miniaturka
    -0.48
     methodological
    -0.47
     Turquía
    -0.46
    woods
    -0.46
    POSITIVE LOGITS
     pregnancy
    0.47
     resourceCulture
    0.41
    JsonFormat
    0.40
     pleaſure
    0.40
     juſ
    0.40
     faſt
    0.40
     purpoſe
    0.35
     Pregnancy
    0.35
     plans
    0.33
    expiresIn
    0.33
    Activations Density 0.009%

    No Known Activations