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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15629
    Prev
    Next
    INDEX
    Explanations

    the term "the" as a significant indicator in various contexts

    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
     propOrder
    -0.83
    ----</
    -0.76
    KommentareTeilen
    -0.64
     defaultstate
    -0.64
     initComponents
    -0.60
    WebServlet
    -0.59
     tartalomajánló
    -0.58
     pinulongan
    -0.58
    Билгалдахарш
    -0.57
    migrationBuilder
    -0.57
    POSITIVE LOGITS
    Almost
    0.38
     Insgesamt
    0.38
    capaian
    0.36
    .
    0.35
     absorción
    0.35
     comparación
    0.34
    ToEnd
    0.33
    resión
    0.33
     transición
    0.32
     fehlt
    0.32
    Activations Density 1.160%

    No Known Activations