Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1006
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "System" in various contexts related to programming

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

    System.out.println

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brigens
    -0.46
    <h3>
    -0.45
     Backman
    -0.42
    </tr>
    -0.39
     OMITBAD
    -0.39
     ČR
    -0.39
     Spitz
    -0.38
    WebServlet
    -0.37
    OrEqual
    -0.37
     ollut
    -0.36
    POSITIVE LOGITS
    System
    1.07
     System
    0.82
     FontWeight
    0.76
     ſind
    0.73
     iſt
    0.69
     syste
    0.68
     Syst
    0.66
    getSystem
    0.65
    GroupLayout
    0.64
     SYSTEM
    0.64
    Activations Density 0.002%

    No Known Activations