© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4568
    Prev
    Next
    INDEX
    Explanations

    instances of the word "simply" and its variations in context, often highlighting simplicity or straightforwardness in explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.67
    __':
    -0.67
     initComponents
    -0.65
    __":
    
    -0.65
    __':
    
    -0.59
     useAppContext
    -0.59
    SharedCtor
    -0.57
     فريبيس
    -0.56
     Jefus
    -0.56
    wapV
    -0.55
    POSITIVE LOGITS
     simply
    1.34
    simply
    1.23
    Simply
    1.17
     Simply
    1.14
     simplemente
    0.91
     simplesmente
    0.85
     simplement
    0.84
     merely
    0.82
     semplicemente
    0.79
     просто
    0.71
    Activations Density 0.156%

    No Known Activations