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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 20
    Prev
    Next
    INDEX
    Explanations

    conversations about parenting and child care practices

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

    words and phrases related to diapers, babies, and parenting.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    terms and concepts related to diapers, parenting, and baby care products.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Paglinawan
    -0.62
    IntoConstraints
    -0.53
    Selfer
    -0.49
    pasto
    -0.46
     Vegetation
    -0.45
    olisian
    -0.45
     Italijani
    -0.44
    ignan
    -0.44
     bocetos
    -0.44
    SerializedName
    -0.43
    POSITIVE LOGITS
     baby
    0.69
     infant
    0.64
     Baby
    0.60
     infants
    0.56
    Baby
    0.55
     Infant
    0.54
    baby
    0.54
     bébé
    0.53
     babies
    0.53
     toddler
    0.52
    Activations Density 0.142%

    No Known Activations