© 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. 21-GEMMASCOPE-RES-16K
    11. 12800
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax in programming languages

    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
    ennom
    -0.51
    abancı
    -0.49
     Zü
    -0.46
    Ingrédients
    -0.43
    ディション
    -0.43
    וויק
    -0.42
    γωγ
    -0.41
    haupt
    -0.41
    mobileqq
    -0.41
     consideration
    -0.40
    POSITIVE LOGITS
     print
    2.06
    print
    2.05
     Print
    1.75
     prints
    1.74
     PRINT
    1.68
    Print
    1.66
     printing
    1.57
     println
    1.55
    PRINT
    1.55
     printf
    1.54
    Activations Density 0.300%

    No Known Activations