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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12357
    Prev
    Next
    INDEX
    Explanations

    function calls and mathematical operations in code contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.62
    principalTable
    -0.62
     rowspan
    -0.58
    serviceWorker
    -0.53
    PerformLayout
    -0.51
    SpringBootTest
    -0.51
    stateMutability
    -0.50
    toThrow
    -0.49
    GenerationType
    -0.49
     <<<<<<<<<<<<<<
    -0.48
    POSITIVE LOGITS
     кӀ
    0.66
    udesta
    0.63
     quæ
    0.61
    __*/
    0.60
     Jérusalem
    0.60
     bestemt
    0.57
    ptonshire
    0.57
     wikipagina
    0.57
    Życiorys
    0.56
     Paglinawan
    0.55
    Activations Density 0.512%

    No Known Activations