© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14700
    Prev
    Next
    INDEX
    Explanations

    terms related to pregnancy and motherhood experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onError
    -0.30
    ByType
    -0.29
    ьаж
    -0.28
    usakan
    -0.28
     merusak
    -0.26
    IntoConstraints
    -0.26
    titleMargin
    -0.26
    notFound
    -0.26
    opis
    -0.25
    hütte
    -0.25
    POSITIVE LOGITS
     pregnancy
    2.44
     pregnant
    2.34
     Pregnancy
    2.20
    Pregnancy
    2.11
     Pregnant
    2.08
    pregnancy
    2.06
    pregnant
    2.05
     pregnancies
    1.94
     maternity
    1.88
     embarazo
    1.78
    Activations Density 0.682%

    No Known Activations