© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2310
    Prev
    Next
    INDEX
    Explanations

    formal addresses and references to authority

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

    formal titles of address and respect (Your Honor, Your Majesty).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.40
    ništvo
    -0.35
     syke
    -0.35
     frenos
    -0.35
     Anbieter
    -0.34
     complicado
    -0.34
     ženy
    -0.33
    ไทย
    -0.33
    ynku
    -0.32
    inguém
    -0.32
    POSITIVE LOGITS
     Excellency
    1.11
     His
    1.03
     Excell
    0.98
     Majesty
    0.95
    His
    0.95
    Excell
    0.94
     excell
    0.94
     Highness
    0.91
     GenerationType
    0.87
     Honorable
    0.84
    Activations Density 0.157%

    No Known Activations