© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1223
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure elements

    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
    </code>
    -0.52
     negozi
    -0.45
     mû
    -0.44
     súčas
    -0.43
     préfé
    -0.43
     hjel
    -0.42
    γα
    -0.41
    llings
    -0.40
     nás
    -0.40
    以此
    -0.40
    POSITIVE LOGITS
     виправивши
    1.03
    1.00
    WithIOException
    0.90
    ?

    0.89
    __":

    0.86
    :✨
    0.84
    */

    0.84
    )

    0.83
    <>

    0.83
     EconPapers
    0.83
    Activations Density 0.078%
    No Known Activations