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. 33-GEMMASCOPE-RES-16K
    6. 8022
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.46
     utafitiHapana
    -0.42
    ListItemIcon
    -0.41
    reportWebVitals
    -0.41
    HtmlAttribute
    -0.40
    AnchorTagHelper
    -0.40
    XtraReports
    -0.35
    EFIAPI
    -0.35
    XtraBars
    -0.34
     RoutedEventArgs
    -0.34
    POSITIVE LOGITS
     countries
    2.03
     cities
    1.88
     regions
    1.84
     region
    1.81
    countries
    1.80
     counties
    1.75
     country
    1.73
     provinces
    1.73
    Countries
    1.70
     Countries
    1.68
    Activations Density 1.455%

    No Known Activations