Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9368
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in code snippets

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

    Code snippets, often involving functions or options

    np_acts-logits-general · gemini-2.0-flash

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}$}
    -0.95
    .")
    
    -0.91
    ^(@)
    -0.86
     $_"
    -0.82
    }.
    
    -0.81
     \\
    
    -0.79
    >\<^
    -0.79
    ſelves
    -0.77
     photolibrary
    -0.77
    &
    
    -0.76
    POSITIVE LOGITS
    ↵
    0.84
     {
    0.76
    <eos>
    0.74
     ...
    0.66
    </em>
    0.65
    "
    0.65
     @
    0.64
    addContainerGap
    0.63
    ()
    0.61
    {
    0.59
    Activations Density 0.724%

    No Known Activations