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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1178
    Prev
    Next
    INDEX
    Explanations

    references to kings, particularly the character King Kong and similar royal titles

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

    "King" or similar royal titles

    np_acts-logits-general · gemini-2.0-flash

    King Kong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    CloseOperation
    -0.61
     Zacks
    -0.58
     pleaſure
    -0.55
     leſs
    -0.55
    $__
    -0.54
     Whistler
    -0.54
    处的
    -0.52
     pinulongan
    -0.51
    GRAP
    -0.51
     compri
    -0.51
    POSITIVE LOGITS
    👑
    0.74
     Kings
    0.73
     KING
    0.72
     King
    0.71
     Queen
    0.69
     Koenig
    0.67
    pin
    0.66
    🤴
    0.64
     kings
    0.64
     monarch
    0.64
    Activations Density 0.076%

    No Known Activations