Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2404
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and syntax structures

    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
     referenties
    -0.40
     internas
    -0.33
    Bronnen
    -0.33
    HtmlAttribute
    -0.33
    apiUrl
    -0.33
    zong
    -0.32
    __;
    -0.32
    Bet
    -0.31
    <tbody>
    -0.31
     Bet
    -0.31
    POSITIVE LOGITS
    httphttps
    0.61
    RefNanny
    0.56
    ürlich
    0.51
     PhpStorm
    0.50
    новништво
    0.48
    GEBURTSDATUM
    0.47
    Хьажоргаш
    0.47
    findpost
    0.46
    WithIOException
    0.46
    IndentedString
    0.46
    Activations Density 0.074%

    No Known Activations