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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4210
    Prev
    Next
    INDEX
    Explanations

    discussions focused on the concept of "order" 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.51
    
    -0.47
    IBarButtonItem
    -0.45
     smtplib
    -0.44
     propOrder
    -0.44
     bParam
    -0.42
    ItemLayout
    -0.42
    DrawerToggle
    -0.41
    Rüyada
    -0.41
    TagMode
    -0.40
    POSITIVE LOGITS
     level
    0.67
     areas
    0.60
    level
    0.55
    
    0.53
    VERSION
    0.52
    BackgroundColor
    0.49
     neceſſ
    0.48
     surface
    0.48
     prestige
    0.48
     typelib
    0.48
    Activations Density 0.208%

    No Known Activations