© 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. 19-GEMMASCOPE-RES-16K
    11. 3502
    Prev
    Next
    INDEX
    Explanations

    instances of repetition or return, particularly in actions, emotions, or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.64
    цездатний
    -0.60
     بيها
    -0.59
     كومونز
    -0.58
    ronique
    -0.57
     censiti
    -0.56
    MIDDLEWARE
    -0.56
     Biôgrafia
    -0.55
     TextAppearance
    -0.55
    efits
    -0.55
    POSITIVE LOGITS
     again
    4.30
    again
    3.83
    Again
    3.71
     Again
    3.63
     AGAIN
    3.28
     novamente
    3.17
     nuevamente
    2.96
     nuovamente
    2.77
     снова
    2.66
     опять
    2.60
    Activations Density 1.460%

    No Known Activations