© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4052
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to significant entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Jährige
    -0.70
     Hinsicht
    -0.62
     poucos
    -0.60
     humains
    -0.60
     preuves
    -0.57
     marquées
    -0.56
     chrétiens
    -0.56
     élevées
    -0.55
     réfugiés
    -0.54
     gereken
    -0.52
    POSITIVE LOGITS
     lives
    0.89
     fortunes
    0.87
     antics
    0.78
     activities
    0.72
     minds
    0.71
     actions
    0.70
     affairs
    0.69
     teachings
    0.68
     workings
    0.68
    activities
    0.65
    Activations Density 0.565%

    No Known Activations