© 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. 3-GEMMASCOPE-RES-16K
    11. 8668
    Prev
    Next
    INDEX
    Explanations

    instances of specific prepositions and conjunctions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SaveChangesAsync
    -0.66
    setVerticalGroup
    -0.59
     AppCompatTheme
    -0.59
     errMsg
    -0.58
     sánchez
    -0.57
    ChildScrollView
    -0.57
    actéristi
    -0.54
    Dichloropropane
    -0.54
     enfans
    -0.54
    fjspx
    -0.54
    POSITIVE LOGITS
    到
    1.66
     zum
    1.59
     zur
    1.52
     към
    1.38
     到
    1.34
     unto
    1.28
     к
    1.27
     إلى
    1.25
     đến
    1.21
     zu
    1.11
    Activations Density 0.068%

    No Known Activations