© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2666
    Prev
    Next
    INDEX
    Explanations

    specific occurrences of events, schedules, plans, and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readystatechange
    -0.57
    libft
    -0.54
    Autoritní
    -0.48
    MetaObject
    -0.44
    +#+
    -0.44
    insics
    -0.43
     الرياضيه
    -0.43
    msgTypes
    -0.42
     OnEnable
    -0.42
    
    -0.42
    POSITIVE LOGITS
     prochain
    0.72
     prossima
    0.67
     prochaines
    0.63
     upcoming
    0.60
     tomorrow
    0.60
     prochaine
    0.58
     próxima
    0.57
     prossimo
    0.54
     sắp
    0.53
     will
    0.52
    Activations Density 0.586%

    No Known Activations