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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29024
    Prev
    Next
    INDEX
    Explanations

    phrases that express self-awareness and contemplation about recent experiences and feelings

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

    recent time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complete
    -0.54
     eventual
    -0.48
     total
    -0.46
     kés
    -0.46
     original
    -0.46
     originally
    -0.45
     a
    -0.44
     eventually
    -0.44
     (
    -0.43
     or
    -0.43
    POSITIVE LOGITS
     lately
    1.50
     Lately
    1.45
    recent
    1.07
    最近
    1.05
    recently
    1.01
    Recently
    0.96
     récente
    0.95
    Recent
    0.94
     recent
    0.94
     betweenstory
    0.94
    Activations Density 0.106%

    No Known Activations