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. 12727
    Prev
    Next
    INDEX
    Explanations

    references to past experiences and personal anecdotes

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

    Recollections or memories

    np_acts-logits-general · gemini-2.0-flash

    recalling past times

    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
     currently
    -0.79
     recent
    -0.77
     bisher
    -0.77
     derzeit
    -0.76
    目前
    -0.72
     momentan
    -0.72
     đang
    -0.70
     Currently
    -0.70
     Recent
    -0.69
     AssemblyCulture
    -0.67
    POSITIVE LOGITS
    那时候
    1.18
    当時は
    1.08
     damals
    1.03
     помню
    0.98
    那时
    0.93
     damal
    0.90
    当时的
    0.86
    当時
    0.84
     damaligen
    0.84
    当時の
    0.83
    Activations Density 0.393%

    No Known Activations