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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 1392
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific health-related subjects and societal commentary, particularly focusing on politics, culture, and social issues

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

    Follows nouns, often at the end of sentences or phrases

    np_acts-logits-general · gemini-2.0-flash

    medical, technical, and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ་་
    -1.18
     Мексичка
    -1.12
    etheless
    -1.00
     crdi
    -0.98
     photolibrary
    -0.98
     ſind
    -0.97
     NSCoder
    -0.96
     '\\;'
    -0.94
     ―――――
    -0.94
     Forumite
    -0.93
    POSITIVE LOGITS
    ↵↵
    0.94
    ↵
    0.92
     (
    0.85
    .
    0.81
     
    0.80
    <eos>
    0.70
    :
    0.69
    ,
    0.68
     is
    0.68
      
    0.66
    Activations Density 2.695%

    No Known Activations