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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 2050
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to kingship and royalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compri
    -0.76
     Lovato
    -0.69
     themſelves
    -0.67
    eradish
    -0.65
     uſ
    -0.65
     fraiche
    -0.65
    scriber
    -0.65
     Dars
    -0.64
     ſeveral
    -0.64
     Travis
    -0.63
    POSITIVE LOGITS
     Kings
    1.50
     kings
    1.45
     KING
    1.38
     King
    1.36
    Kings
    1.27
     king
    1.23
     KINGS
    1.19
    King
    1.12
    👑
    1.10
    kings
    1.07
    Activations Density 0.096%

    No Known Activations