© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 47870
    Prev
    Next
    INDEX
    Explanations

    content related to programming, particularly in C/C++ and Lua languages, including file operations and library inclusions

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

    files and filenames

    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
    webElementXpaths
    -0.81
     AssemblyCulture
    -0.80
    AddTagHelper
    -0.67
    nodoc
    -0.65
     propOrder
    -0.63
    تفصیلات
    -0.60
    transQ
    -0.59
    aarrggbb
    -0.59
    AndEndTag
    -0.55
     للاسماء
    -0.55
    POSITIVE LOGITS
     file
    0.43
     filename
    0.42
     Activity
    0.40
     Files
    0.39
     label
    0.39
    file
    0.39
     Fall
    0.39
     name
    0.37
     Pass
    0.37
     File
    0.37
    Activations Density 0.024%

    No Known Activations