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. 5-GEMMASCOPE-RES-16K
    6. 10298
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to feasibility and optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.64
    Personendaten
    -0.62
    󠁧
    -0.55
    featureID
    -0.55
    **/
    
    -0.55
    PerformLayout
    -0.54
    出版年
    -0.53
    อื่น
    -0.53
     насељу
    -0.53
    =""><
    -0.52
    POSITIVE LOGITS
    TargetException
    0.76
    flashdata
    0.55
    Chham
    0.52
     thereto
    0.52
     Majefty
    0.52
     asap
    0.50
    IntoConstraints
    0.49
     aastal
    0.49
     immediately
    0.48
     ویکی‌آمباردا
    0.47
    Activations Density 0.114%

    No Known Activations