© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4192
    Prev
    Next
    INDEX
    Explanations

    references to "Royal" entities or organizations

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

    institutional names beginning with "Royal" followed by a descriptor word.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.47
     estaremos
    -0.41
     שוליים
    -0.40
    ientôt
    -0.40
     realizarse
    -0.39
    landschaft
    -0.39
    ✷
    -0.39
     Bend
    -0.39
     Darum
    -0.39
     realización
    -0.38
    POSITIVE LOGITS
     royal
    0.84
     Royal
    0.83
    Royal
    0.78
    royal
    0.73
     ROYAL
    0.70
     Royals
    0.58
    皇家
    0.56
    ロイヤル
    0.53
     Royalty
    0.53
     royalty
    0.52
    Activations Density 0.097%

    No Known Activations