© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12026
    Prev
    Next
    INDEX
    Explanations

    terms related to classifiers and feature selection processes in machine learning

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

    classification algorithms and processes

    np_acts-logits-general · gemini-2.0-flash

    classification and classifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    +#+#
    -0.85
     дописавши
    -0.72
     تضيفلها
    -0.67
    ">//
    -0.66
     समीक्षाओं
    -0.66
    IntoConstraints
    -0.63
    principalColumn
    -0.62
     intptr
    -0.60
    
    -0.60
    webElementXpaths
    -0.60
    POSITIVE LOGITS
     classifier
    0.95
     classification
    0.90
     classifying
    0.81
     Classification
    0.81
     Classifier
    0.80
    classifiers
    0.79
     classify
    0.78
     classifiers
    0.78
    classifier
    0.78
     Classi
    0.77
    Activations Density 0.436%

    No Known Activations