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. 14582
    Prev
    Next
    INDEX
    Explanations

    terms related to heat, temperature, and their effects on materials

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

    heat and temperature changes

    np_acts-logits-general · gemini-2.0-flash

    heat and burning sensations

    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
    IUrlHelper
    -0.62
    HomeAsUpEnabled
    -0.60
    
    -0.56
    falfa
    -0.51
     مرئيه
    -0.51
    neum
    -0.50
     chuva
    -0.50
    setVerticalGroup
    -0.49
    Rhestr
    -0.49
    τουργ
    -0.49
    POSITIVE LOGITS
     hot
    0.76
     hotter
    0.74
     scorching
    0.69
    hot
    0.69
    ร้อน
    0.69
     temperature
    0.68
     bỏng
    0.67
     sizzling
    0.67
     burning
    0.66
     Heat
    0.66
    Activations Density 0.266%

    No Known Activations