© 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. 24-GEMMASCOPE-RES-16K
    11. 2103
    Prev
    Next
    INDEX
    Explanations

    phrases related to royal ceremonies and acts of submission

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

    following "with" or related to "respect"

    np_acts-logits-general · gemini-2.0-flash

    respect, politeness, etiquette

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
     <>",
    -0.38
     Diagnos
    -0.38
    iastes
    -0.37
     CreateTagHelper
    -0.36
    ForResult
    -0.35
    Île
    -0.35
     diagnos
    -0.34
     Alem
    -0.33
     Thebes
    -0.33
     prolific
    -0.33
    POSITIVE LOGITS
     respectful
    0.86
     etiquette
    0.82
     salute
    0.80
     respectfully
    0.79
     Etiquette
    0.76
    respect
    0.74
     politeness
    0.74
     Respect
    0.73
    Respect
    0.71
     respetu
    0.71
    Activations Density 0.245%

    No Known Activations