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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6764
    Prev
    Next
    INDEX
    Explanations

    C++ input and output stream commands and operations

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

    "cout" statements in C++ code

    np_acts-logits-general · gemini-2.0-flash

    c++ standard output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slightly
    -0.56
     autorytatywna
    -0.51
     مواليد
    -0.50
    Slightly
    -0.49
     intptr
    -0.48
    izability
    -0.48
    Спољашње
    -0.48
     تضيفلها
    -0.47
    slightly
    -0.46
    自分も
    -0.45
    POSITIVE LOGITS
    cout
    2.41
     cout
    1.77
    Cout
    1.29
     Cout
    1.01
    cerr
    1.00
    iostream
    0.90
     endl
    0.85
    couts
    0.77
     couture
    0.70
     Couture
    0.70
    Activations Density 0.065%

    No Known Activations