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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3762
    Prev
    Next
    INDEX
    Explanations

    references to various institutions and organizations associated with the term "Royal."

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

    Follows "Royal"

    np_acts-logits-general · gemini-2.0-flash

    royal followed by institutional names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.74
     FontWeight
    -0.61
     BnF
    -0.61
     Kości
    -0.60
    nezeu
    -0.59
     مركز
    -0.59
    TestingModule
    -0.57
     Testa
    -0.56
    NegativeButton
    -0.56
     helft
    -0.56
    POSITIVE LOGITS
     Royal
    0.80
    royal
    0.77
    ROY
    0.74
    Royal
    0.72
     ROYAL
    0.69
     royal
    0.68
    Personendaten
    0.68
     Roy
    0.65
    ロイヤル
    0.62
     }{@
    0.62
    Activations Density 0.057%

    No Known Activations