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. 13855
    Prev
    Next
    INDEX
    Explanations

    elements related to file handling and CSV processing in code

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

    File opening/reading operations

    np_acts-logits-general · gemini-2.0-flash

    opening files with 'with'

    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
    brtc
    -0.55
     oprot
    -0.54
    dubbo
    -0.52
    Bioaccumulative
    -0.51
    DeleteBehavior
    -0.50
    =$?
    -0.49
    TypeService
    -0.49
    issor
    -0.49
     Мексичка
    -0.49
    rachtet
    -0.48
    POSITIVE LOGITS
     file
    1.69
     File
    1.49
    file
    1.47
    File
    1.45
     files
    1.37
    FILE
    1.34
     FILE
    1.30
     filename
    1.25
    文件
    1.23
     readFile
    1.22
    Activations Density 0.335%

    No Known Activations