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. 20-GEMMASCOPE-RES-16K
    6. 1540
    Prev
    Next
    INDEX
    Explanations

    key concepts and themes related to healthcare quality and professionalism

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

    importance or necessity

    np_acts-logits-general · gemini-2.0-flash

    ensuring proper understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uterte
    -0.60
    ktop
    -0.59
    Kelebihan
    -0.58
     jLabel
    -0.57
     sánh
    -0.56
    tagHelperRunner
    -0.55
    GEBURTSDATUM
    -0.55
     Правда
    -0.54
    supposed
    -0.52
    ycznie
    -0.51
    POSITIVE LOGITS
     ensuring
    1.19
     proper
    1.19
    Proper
    1.17
     Ensuring
    1.09
     Proper
    1.08
     properly
    1.05
     understanding
    0.99
    proper
    0.98
     ensure
    0.94
     Properly
    0.90
    Activations Density 0.362%

    No Known Activations