© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3041
    Prev
    Next
    INDEX
    Explanations

    references to royal entities, titles, and organizations

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

    "Royal" followed by an organization or entity

    np_acts-logits-general · gemini-2.0-flash

    royal followed by institutions or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.56
    inSlope
    -0.54
    MessageTagHelper
    -0.53
    
    -0.50
    igshid
    -0.47
     ArrayAdapter
    -0.47
     ujednoznacz
    -0.44
     curé
    -0.44
     lende
    -0.43
    ագրություններ
    -0.42
    POSITIVE LOGITS
     Royal
    2.17
    Royal
    2.11
     ROYAL
    2.00
     royal
    2.00
    royal
    1.98
    ロイヤル
    1.54
    皇家
    1.45
     Royals
    1.41
    ROY
    1.36
     royals
    1.34
    Activations Density 0.198%

    No Known Activations