© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3954
    Prev
    Next
    INDEX
    Explanations

    events related to awards or ceremonies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    specific numerical and location context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Negative Logits
    ]='\
    -0.73
     pleaſure
    -0.60
    meanor
    -0.59
    upcoming
    -0.58
    kapan
    -0.58
     ashes
    -0.57
    зулта
    -0.56
     Everywhere
    -0.54
     purpoſe
    -0.53
     forthcoming
    -0.53
    POSITIVE LOGITS
     at
    0.83
     held
    0.64
    ParallelGroup
    0.64
     صوتيه
    0.59
    BufferException
    0.57
    Held
    0.54
     presso
    0.51
    at
    0.51
     tại
    0.50
     housed
    0.46
    Activations Density 0.069%

    No Known Activations