© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3755
    Prev
    Next
    INDEX
    Explanations

    terms related to significant life events and transitions

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

    Events indicating an end or conclusion

    np_acts-logits-general · gemini-2.0-flash

    life milestones and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hnia
    -0.68
     createState
    -0.61
     OFDb
    -0.57
    GHIJKLM
    -0.56
    died
    -0.55
    роди
    -0.55
    matician
    -0.55
    oplayer
    -0.54
    .*")]
    -0.53
     désolés
    -0.53
    POSITIVE LOGITS
     ceremony
    0.88
     ceremonies
    0.73
     date
    0.70
     Ceremony
    0.64
     announcement
    0.63
     pangs
    0.63
     celebrations
    0.61
    zeit
    0.60
     process
    0.59
     avven
    0.56
    Activations Density 0.595%

    No Known Activations