© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11343
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to defining and managing data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related symbols and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.89
     ExecuteAsync
    -0.81
    RegressionTest
    -0.79
    '},
    
    -0.77
     Савезне
    -0.76
    GOTREF
    -0.72
     tartalomajánló
    -0.71
     @}
    -0.69
    .)}
    -0.69
    ."]
    -0.68
    POSITIVE LOGITS
    //
    1.23
     //
    1.22
    ){//
    1.12
     {//
    1.07
    ;//
    1.01
    /*
    0.93
    {//
    0.91
     /*
    0.91
    );//
    0.90
    <!--
    0.87
    Activations Density 0.908%

    No Known Activations