© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1130
    Prev
    Next
    INDEX
    Explanations

    references to royal or historical buildings and estates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.42
    новништво
    -0.41
    Personensuche
    -0.40
    ंदीखरीदारी
    -0.40
    Retail
    -0.39
     Retailers
    -0.38
    PERATURE
    -0.38
     utafitiHapana
    -0.36
    cities
    -0.36
    ANTLR
    -0.35
    POSITIVE LOGITS
     estate
    1.30
     Estate
    1.14
     manor
    1.07
     mansion
    1.06
     estates
    1.05
    Estate
    1.05
     ESTATE
    1.04
    estate
    0.98
     Manor
    0.85
     palace
    0.83
    Activations Density 0.401%

    No Known Activations