© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13477
    Prev
    Next
    INDEX
    Explanations

    elements of HTML code that signify various UI components or interactive elements in a webpage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -1.03
    Билгалдахарш
    -1.00
     CallOverrides
    -0.99
     kaarangay
    -0.97
    endpush
    -0.97
    Derbyniad
    -0.97
     queſta
    -0.97
     שוליים
    -0.94
    Хьажоргаш
    -0.93
    MigrationBuilder
    -0.92
    POSITIVE LOGITS
     the
    0.44
     a
    0.35
    <blockquote>
    0.32
     an
    0.32
     stehen
    0.31
    แพ
    0.28
    the
    0.27
    Order
    0.27
    <td>
    0.27
     apporter
    0.27
    Activations Density 0.033%

    No Known Activations