© 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. 859
    Prev
    Next
    INDEX
    Explanations

    references to classes and attributes in programming, particularly in Java

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

    "class" in code or text

    np_acts-logits-general · gemini-2.0-flash

    class

    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
     sputnik
    -0.54
    XtraReports
    -0.53
     Roth
    -0.50
    Roth
    -0.49
    rogels
    -0.49
     Sputnik
    -0.48
     corne
    -0.47
     Budgets
    -0.47
    quehanna
    -0.46
    paramInt
    -0.46
    POSITIVE LOGITS
     class
    2.63
    class
    2.39
     Class
    2.36
     CLASS
    2.35
    Class
    2.26
    CLASS
    2.24
     classe
    2.14
     classes
    2.11
     clase
    1.96
     Classes
    1.95
    Activations Density 0.198%

    No Known Activations