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. 8-GEMMASCOPE-RES-16K
    6. 307
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes related to dropdown lists and selections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ℚ
    -0.35
    LoggerFactory
    -0.34
     asics
    -0.33
     MessageType
    -0.31
     tissue
    -0.31
     skull
    -0.29
     réus
    -0.28
     herd
    -0.27
     skeletons
    -0.27
    lardır
    -0.27
    POSITIVE LOGITS
     JComboBox
    1.19
    JComboBox
    1.11
    ComboBox
    1.05
    bobox
    1.03
    Dropdown
    0.94
    dropdown
    0.92
     Dropdown
    0.91
    DropDownList
    0.90
    comboBox
    0.89
     dropdown
    0.89
    Activations Density 0.235%

    No Known Activations