© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5946
    Prev
    Next
    INDEX
    Explanations

    terms related to formal declarations or apologies in a royal or noble context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.55
    thâu
    -0.55
    EDEFAULT
    -0.55
     IBA
    -0.54
    rungsseite
    -0.54
    WriteTagHelper
    -0.52
    انيف
    -0.51
    wpi
    -0.51
    AddTagHelper
    -0.51
    XmlAccessType
    -0.51
    POSITIVE LOGITS
     royal
    2.28
     king
    2.21
     King
    2.05
    royal
    1.91
     kings
    1.87
     queen
    1.82
     royals
    1.82
    King
    1.81
     royalty
    1.79
     prince
    1.77
    Activations Density 0.442%

    No Known Activations