© 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. 9-GEMMASCOPE-RES-16K
    11. 6287
    Prev
    Next
    INDEX
    Explanations

    references to land and its various aspects, including ownership, use, and related economic terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.54
     linkovi
    -0.54
    ppio
    -0.54
    
    -0.53
    Jîn
    -0.51
    petito
    -0.50
    Fro
    -0.50
     Wicidata
    -0.50
    icles
    -0.50
     veck
    -0.49
    POSITIVE LOGITS
     land
    2.09
     Land
    1.85
    Land
    1.77
     LAND
    1.69
     lands
    1.50
    land
    1.48
    LAND
    1.30
     Lands
    1.27
    土地
    1.15
    lands
    1.14
    Activations Density 0.095%

    No Known Activations