© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9853
    Prev
    Next
    INDEX
    Explanations

    questions or statements regarding themes of morality and human behavior

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Baillargeon
    -0.63
    ModelSerializer
    -0.61
    complexContent
    -0.53
     GRATU
    -0.50
    hoea
    -0.50
    Джерела
    -0.49
     Witkin
    -0.49
     PARSER
    -0.49
     sobald
    -0.48
     forerunner
    -0.47
    POSITIVE LOGITS
     after
    2.70
    after
    2.37
     After
    2.18
    After
    2.11
    AFTER
    1.88
     dopo
    1.78
     après
    1.77
     AFTER
    1.75
     después
    1.64
     setelah
    1.56
    Activations Density 0.241%

    No Known Activations