© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15509
    Prev
    Next
    INDEX
    Explanations

    specific prepositions and their relevant context in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     líqu
    -0.38
     toallas
    -0.33
    مراجع
    -0.33
     oculto
    -0.33
     relojes
    -0.32
     nueces
    -0.31
     ferons
    -0.31
     acompañ
    -0.31
     arbejds
    -0.31
    MathML
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    0.67
    setupUi
    0.66
    !")
    
    0.63
    呌
    0.62
    ImageContext
    0.61
    adpleegd
    0.60
    汌
    0.60
    ressional
    0.59
     ब्रेकडाउन
    0.59
     typelib
    0.57
    Activations Density 0.521%

    No Known Activations