© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13681
    Prev
    Next
    INDEX
    Explanations

    mentions of financial performance and business success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows prepositions like "across," and relates to multiple locations

    np_acts-logits-general · gemini-2.0-flash

    across countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.44
    XtraBars
    -0.43
     fotball
    -0.33
     ziren
    -0.33
    IBOutlet
    -0.33
    Scénario
    -0.32
    TimePicker
    -0.32
    TemporalType
    -0.32
    ære
    -0.32
    huana
    -0.32
    POSITIVE LOGITS
     overseas
    1.78
     abroad
    1.63
     countries
    1.45
     Overseas
    1.45
     international
    1.43
    Overseas
    1.42
     Abroad
    1.38
     worldwide
    1.38
    countries
    1.37
     Europe
    1.34
    Activations Density 2.173%

    No Known Activations