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. 92153
    Prev
    Next
    INDEX
    Explanations

    representations of lists and list comprehensions in code

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

    set notation

    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
    nezeu
    -0.60
    StructEnd
    -0.57
    eqref
    -0.54
    fromnode
    -0.52
     للاسماء
    -0.50
    ViewImports
    -0.50
     endfor
    -0.49
    Personendaten
    -0.49
     forState
    -0.48
     eventName
    -0.47
    POSITIVE LOGITS
    SELECT
    0.34
     câte
    0.34
    copy
    0.34
     Suom
    0.34
    rijf
    0.34
     Portuguesa
    0.34
    present
    0.33
     tkinter
    0.33
    function
    0.33
    Aiheesta
    0.32
    Activations Density 0.042%

    No Known Activations