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. 13841
    Prev
    Next
    INDEX
    Explanations

    positive numerical values, particularly in pricing or scoring contexts

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

    Numbers as dollar values

    np_acts-logits-general · gemini-2.0-flash

    numbers and currency units

    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
    Personendaten
    -0.98
    addCriterion
    -0.96
    Tazama
    -0.95
     pinulongan
    -0.94
    تقاوى
    -0.88
    ⓧ
    -0.87
     تانيه
    -0.87
     esternos
    -0.85
    setVerticalGroup
    -0.84
    AutoField
    -0.84
    POSITIVE LOGITS
    0
    0.50
    لاق
    0.45
    ToString
    0.44
    5
    0.42
    AssignableFrom
    0.39
    Blo
    0.38
    سب
    0.38
    brido
    0.37
    6
    0.37
    扭
    0.37
    Activations Density 0.180%

    No Known Activations