© 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. 24-GEMMASCOPE-RES-16K
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    references to the term "Royal" in various contexts

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

    Follows "Royal"

    np_acts-logits-general · gemini-2.0-flash

    Royal followed by institution names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.69
    Демографія
    -0.64
    GenerationType
    -0.64
     ProtoMessage
    -0.61
     NgModule
    -0.58
     Público
    -0.58
    erializer
    -0.57
    extAlignment
    -0.56
    nezeu
    -0.52
     just
    -0.51
    POSITIVE LOGITS
    ties
    0.60
    новниш
    0.58
    ########.
    0.58
    glPushMatrix
    0.56
     canin
    0.55
     Highness
    0.54
     Mail
    0.54
     flush
    0.53
     Flush
    0.52
    lieu
    0.52
    Activations Density 0.127%

    No Known Activations