© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 24812
    Prev
    Next
    INDEX
    Explanations

    instances of the word "born" and its variations, indicating a focus on themes of birth, rebirth, and origin

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

    born

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     OkHttpClient
    -0.45
     Polda
    -0.45
     Gnade
    -0.45
    ytä
    -0.42
     hjel
    -0.42
    område
    -0.41
     Tafel
    -0.41
    bledon
    -0.41
    君子
    -0.41
    ctools
    -0.41
    POSITIVE LOGITS
     born
    1.03
     birth
    0.94
    Birth
    0.90
     BORN
    0.89
     Birth
    0.89
    born
    0.87
     Born
    0.86
    birth
    0.85
     lahir
    0.85
    Born
    0.84
    Activations Density 0.022%

    No Known Activations