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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 113976
    Prev
    Next
    INDEX
    Explanations

    import statements in programming code

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

    code imports and includes

    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
     pleaſure
    -0.69
    Personendaten
    -0.66
     queſta
    -0.63
    曖昧さ回避
    -0.59
    ]")]
    -0.58
    Dış
    -0.57
    greenrobot
    -0.57
     שוליים
    -0.56
     itſelf
    -0.55
    queryInterface
    -0.55
    POSITIVE LOGITS
    import
    1.23
     import
    0.71
    ThroughAttribute
    0.56
    Import
    0.52
    ://
    0.50
    __(/*!
    0.49
     importing
    0.48
     Import
    0.47
     imported
    0.47
     Importing
    0.45
    Activations Density 0.001%

    No Known Activations