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. 20-GEMMASCOPE-RES-16K
    6. 11075
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey high praise or admiration

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

    an impressive quantity or quality

    np_acts-logits-general · gemini-2.0-flash

    incredible/amazing/immense + noun

    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
    SequentialGroup
    -0.52
    bacillus
    -0.48
     весьма
    -0.46
     elég
    -0.46
     durchaus
    -0.46
    ည်
    -0.46
     dość
    -0.45
    そろそろ
    -0.45
     umum
    -0.45
    Sortie
    -0.44
    POSITIVE LOGITS
     amounts
    1.03
     Amounts
    0.94
     amount
    0.94
    amounts
    0.91
    кновен
    0.90
     feats
    0.90
     وتسجيلات
    0.88
    ulously
    0.84
     🤩
    0.81
     Amount
    0.81
    Activations Density 0.170%

    No Known Activations