© 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. 35-GEMMASCOPE-RES-16K
    6. 14797
    Prev
    Next
    INDEX
    Explanations

    the use of the term "etc" to indicate continuation or examples in a list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.61
    CloseOperation
    -0.59
    aarrggbb
    -0.57
     <=",
    -0.54
    __":
    
    -0.54
    әрмәләр
    -0.54
     Majefty
    -0.54
     queſta
    -0.54
     المعيارى
    -0.54
    TagMode
    -0.52
    POSITIVE LOGITS
    etera
    0.91
    々
    0.50
    eter
    0.46
    pp
    0.42
     pp
    0.38
     PP
    0.36
    etra
    0.36
     passim
    0.35
    PP
    0.34
    등
    0.34
    Activations Density 0.122%

    No Known Activations