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. 31-GEMMASCOPE-RES-16K
    6. 16332
    Prev
    Next
    INDEX
    Explanations

    function declarations and assertions in code

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

    Code related to testing functions

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nosotros
    -0.33
    ToReturn
    -0.32
    pexpr
    -0.31
    ownic
    -0.29
    SafeAreaView
    -0.27
     cland
    -0.27
     implementing
    -0.27
     binnen
    -0.27
     trả
    -0.25
    }{*}{}
    -0.25
    POSITIVE LOGITS
    RegressionTest
    0.70
    GEBURTSDATUM
    0.69
    SequentialGroup
    0.66
     test
    0.65
     HasFactory
    0.64
     тест
    0.62
     testar
    0.60
    test
    0.60
    Test
    0.59
     Test
    0.58
    Activations Density 0.194%

    No Known Activations