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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1435
    Prev
    Next
    INDEX
    Explanations

    references to academic and administrative procedures related to student records and belongings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.63
    reactstrap
    -0.56
    CppMethod
    -0.56
    TagMode
    -0.54
    bkz
    -0.53
    Vidite
    -0.53
    Билгалдахарш
    -0.52
     Walkover
    -0.52
    naires
    -0.52
    Наводи
    -0.51
    POSITIVE LOGITS
     payment
    0.56
     payments
    0.46
     goederen
    0.43
    payment
    0.43
     Payment
    0.41
     PAYMENT
    0.41
     owed
    0.39
     refund
    0.39
    Payment
    0.38
     repayment
    0.38
    Activations Density 0.320%

    No Known Activations