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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10717
    Prev
    Next
    INDEX
    Explanations

    references to royalty and royal figures, particularly Prince Harry and Meghan Markle

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

    Prince Harry and Meghan Markle

    np_acts-logits-general · gemini-2.0-flash

    Duke and Duchess of Sussex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    medim
    -0.41
     Ause
    -0.38
    municipi
    -0.38
     excru
    -0.38
     стаття
    -0.38
    Дереккөздер
    -0.36
    SourceChecksum
    -0.36
     <>",
    -0.36
    peen
    -0.35
     boss
    -0.35
    POSITIVE LOGITS
     مرئيه
    0.65
     betweenstory
    0.63
     royal
    0.56
     <<<<<<<<<<<<<<
    0.54
     royals
    0.54
     ostavi
    0.51
    ().__
    0.48
     InputDecoration
    0.47
     Inscrivez
    0.47
     ROYAL
    0.46
    Activations Density 0.103%

    No Known Activations