© 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. 12-GEMMASCOPE-RES-16K
    6. 1560
    Prev
    Next
    INDEX
    Explanations

    instances of HTML or XML tags within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.37
     revisor
    -0.36
    ագրություններ
    -0.36
    sepatu
    -0.34
    épend
    -0.34
     vrijwilli
    -0.34
     pemasaran
    -0.33
     везе
    -0.32
     nauczy
    -0.32
     regalías
    -0.32
    POSITIVE LOGITS
    expandindo
    0.73
    :✨
    0.70
    AndEndTag
    0.65
     ویکی‌پدی
    0.65
     שוליים
    0.64
     pinulongan
    0.61
    NameInMap
    0.57
     kasarigan
    0.54
    esserung
    0.49
     Roskov
    0.49
    Activations Density 0.780%

    No Known Activations