© 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 EvalsExportsAPI 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. 5634
    Prev
    Next
    INDEX
    Explanations

    elements of code related to function definitions and variable assignments

    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
     im
    -0.77
     "
    -0.73
     Cap
    -0.73
     Pre
    -0.71
     E
    -0.70
     Pro
    -0.70
     qu
    -0.69
     N
    -0.69
     co
    -0.68
     vi
    -0.67
    POSITIVE LOGITS
     myſelf
    1.37
     pleaſure
    1.37
     itſelf
    1.31
     greateſt
    1.29
     ſtate
    1.27
     Monfieur
    1.24
     auffi
    1.22
     reaſon
    1.22
     poffible
    1.20
     purpoſe
    1.19
    Activations Density 0.399%

    No Known Activations