© 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. 16-GEMMASCOPE-RES-16K
    11. 12564
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles that indicate spatial or relational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grüsse
    -0.60
    acidade
    -0.47
    RegressionTest
    -0.47
     estreia
    -0.46
     respecto
    -0.45
     oração
    -0.44
     gdy
    -0.44
     aprendizagem
    -0.43
     tatuagens
    -0.43
     bandeira
    -0.42
    POSITIVE LOGITS
     Houſe
    0.62
     useContext
    0.58
     Majefty
    0.52
    addPreferredGap
    0.51
     CanadaChoose
    0.51
    addGap
    0.50
     involved
    0.50
     находится
    0.49
     AssemblyVersion
    0.48
     BorderSide
    0.47
    Activations Density 0.189%

    No Known Activations