© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15965
    Prev
    Next
    INDEX
    Explanations

    references to practices and methodologies in various contexts

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

    before "Practice" or "practice"

    np_acts-logits-general · gemini-2.0-flash

    practice guidelines and contexts

    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
     المعرف
    -0.69
    erequisites
    -0.61
    erequisite
    -0.56
    IDATE
    -0.56
    სქოლიო
    -0.56
    mobileqq
    -0.55
    SerializeField
    -0.55
    Cyfeiriadau
    -0.55
    WebpackPlugin
    -0.53
     полиции
    -0.53
    POSITIVE LOGITS
     practices
    0.86
    Practices
    0.79
     Practices
    0.77
     PRACTICE
    0.75
     exemplaires
    0.72
     Practice
    0.72
     practise
    0.72
     practice
    0.69
    PRACTICE
    0.68
    practices
    0.68
    Activations Density 0.046%

    No Known Activations