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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3202
    Prev
    Next
    INDEX
    Explanations

    references to console commands and methods in programming contexts

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

    Follows "Console" or "." and precedes "WriteLine"

    np_acts-logits-general · gemini-2.0-flash

    Console WriteLine

    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
    IsContent
    -0.70
     مشين
    -0.64
    tanleria
    -0.62
    fjspx
    -0.61
     SafeMath
    -0.61
    ParallelGroup
    -0.61
    SizeMode
    -0.60
    IContainer
    -0.56
    principalColumn
    -0.56
    MessageOf
    -0.56
    POSITIVE LOGITS
    ReadLine
    0.68
    bbene
    0.55
    ViewFeatures
    0.53
    NOST
    0.52
    BagLayout
    0.51
     write
    0.51
    WriteLine
    0.50
     Write
    0.49
     jsPsych
    0.49
    Попис
    0.48
    Activations Density 0.078%

    No Known Activations