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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 882
    Prev
    Next
    INDEX
    Explanations

    coding syntax elements and class structures in programming

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

    elements and attributes related to XML configuration files in Java

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

    programming lessons or exercises

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     mapStateToProps
    -0.50
    AccessorTable
    -0.48
     dikem
    -0.46
    SOUNDBITE
    -0.46
    zigen
    -0.45
    forRoot
    -0.43
    Trama
    -0.42
     gué
    -0.42
    Сюжет
    -0.42
     trous
    -0.42
    POSITIVE LOGITS
     lesson
    0.93
     CWE
    0.92
     Lesson
    0.85
    lesson
    0.81
     lessons
    0.74
     Chapter
    0.74
    Lesson
    0.73
    Exercise
    0.73
     exercise
    0.73
     Exercise
    0.71
    Activations Density 0.074%

    No Known Activations