© 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. 23-GEMMASCOPE-RES-16K
    11. 11819
    Prev
    Next
    INDEX
    Explanations

    closing braces and related syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    else
    -0.68
    addCriterion
    -0.56
     BoxFit
    -0.55
    awtextra
    -0.53
     pro
    -0.48
    IsContent
    -0.46
    Morfologia
    -0.46
    catch
    -0.45
    elif
    -0.45
     EconPapers
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.78
     AspNetCore
    0.68
    المناصب
    0.62
     חיצוניים
    0.62
    adpleegd
    0.60
    Portail
    0.57
     مفص
    0.57
    pendente
    0.57
    niająca
    0.56
    zä
    0.55
    Activations Density 0.304%

    No Known Activations