© 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. 2-GEMMASCOPE-RES-16K
    6. 8325
    Prev
    Next
    INDEX
    Explanations

    strings representing output operations or comments in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.75
    ValueStyle
    -0.62
    SharedDtor
    -0.59
     {},
    
    -0.54
     [],
    
    -0.50
     disambiguazione
    -0.49
    windowFixed
    -0.49
    uxxxx
    -0.49
     Wikimedijinoj
    -0.49
     [];
    
    -0.48
    POSITIVE LOGITS
    ----------------
    0.76
    <<
    0.70
     /*
    0.62
    /*
    0.61
     <<
    0.57
    Restore
    0.52
     restore
    0.52
    ++++++++++++++++
    0.49
     Restore
    0.47
    restore
    0.47
    Activations Density 0.230%

    No Known Activations