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. 0-GEMMASCOPE-RES-16K
    6. 6299
    Prev
    Next
    INDEX
    Explanations

    instances of template syntax or variable definitions in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -1.03
    انيف
    -0.89
     lenker
    -0.88
     Мексичка
    -0.88
     nahilalakip
    -0.85
     мәкал
    -0.84
    :✨
    -0.84
     nakalista
    -0.82
     препратки
    -0.81
    fromnode
    -0.80
    POSITIVE LOGITS
    {{
    0.81
     varies
    0.63
     vary
    0.62
     depended
    0.62
     grecque
    0.60
     dipende
    0.60
     asiatique
    0.59
     depends
    0.59
     dipendenti
    0.59
    {{\
    0.58
    Activations Density 0.143%

    No Known Activations