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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 3714
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, specifically related to set notation and expressions involving functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    }}/>
    -0.90
    Datuak
    -0.89
     Wikimedijinoj
    -0.88
    writeFieldEnd
    -0.87
    ]]=
    -0.81
     للمعارف
    -0.80
    脚注の使い方
    -0.74
     '\\;'
    -0.72
     surla
    -0.71
    NTIS
    -0.71
    POSITIVE LOGITS
     kılı
    0.62
    {
    0.59
     {
    0.58
    <h2>
    0.55
     utford
    0.51
     mukana
    0.50
    NSIndexPath
    0.50
     don
    0.50
    {{
    0.48
    {
    
    0.48
    Activations Density 0.336%

    No Known Activations