© 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. 36-GEMMASCOPE-RES-16K
    11. 8024
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NSNotification
    -0.37
    CompilerServices
    -0.37
    ➩
    -0.36
    Datuak
    -0.36
    Бахар
    -0.35
     Amongst
    -0.34
    CppMethod
    -0.32
     Among
    -0.31
     paramInt
    -0.31
     among
    -0.30
    POSITIVE LOGITS
     accordance
    0.73
    RegressionTest
    0.70
     connection
    0.69
     respect
    0.65
     furtherance
    0.65
     conjunction
    0.63
     lieu
    0.62
     regard
    0.59
     związku
    0.58
     anticipation
    0.58
    Activations Density 0.585%

    No Known Activations