© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1800
    Prev
    Next
    INDEX
    Explanations

    instances of the word "born" or related birth terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCabe
    -0.61
     G
    -0.57
    Xie
    -0.57
    adlo
    -0.55
     Xie
    -0.54
    currentItem
    -0.54
    xel
    -0.53
     L
    -0.53
    setMsg
    -0.52
    uel
    -0.52
    POSITIVE LOGITS
     born
    3.31
     BORN
    3.04
     Born
    2.96
    Born
    2.90
    born
    2.80
    BORN
    2.60
     geboren
    2.05
     nasceu
    1.88
     nacido
    1.86
     født
    1.85
    Activations Density 0.054%

    No Known Activations