© 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. 12-GEMMASCOPE-RES-16K
    11. 12719
    Prev
    Next
    INDEX
    Explanations

    code structure indicators, particularly class and import statements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.70
     jScrollPane
    -0.48
     sumpay
    -0.44
     OMITBAD
    -0.42
    存于互联网档案馆
    -0.42
     Vikipedi
    -0.42
    MessageState
    -0.41
    tonode
    -0.40
     vVar
    -0.40
    
    -0.40
    POSITIVE LOGITS
    package
    1.70
    /*
    1.01
    //
    0.88
     AssemblyTitle
    0.83
     package
    0.83
    /**
    0.75
    #
    0.73
     autorytatywna
    0.68
    Package
    0.66
     Package
    0.64
    Activations Density 0.198%

    No Known Activations