© 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. 22-GEMMASCOPE-RES-16K
    11. 3591
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data manipulations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to spreadsheets

    np_acts-logits-general · gemini-2.0-flash

    Microsoft Excel Sheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wiad
    -0.63
     CWE
    -0.58
    GEBURTS
    -0.52
     AssemblyProduct
    -0.52
    omyia
    -0.50
    GRANTED
    -0.50
    出版年
    -0.50
    urlpatterns
    -0.50
    mainAxisSize
    -0.49
    stateProvider
    -0.49
    POSITIVE LOGITS
     sheet
    1.40
    sheet
    1.34
     Excel
    1.34
    Sheet
    1.34
     Sheet
    1.31
    Excel
    1.25
     sheets
    1.24
     spreadsheet
    1.21
     SHEET
    1.19
    SHEET
    1.17
    Activations Density 0.230%

    No Known Activations