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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 401
    Prev
    Next
    INDEX
    Explanations

    economic and business-related terms and concepts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @joshengels

    terms related to mental health conditions and their implications

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

    concepts related to economics, business, and academic reasoning, particularly focusing on terms like "leaders," "standards," "induction," and "hypothesis."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical jargon and business strategy terminology related to economics, markets, and competition.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    
    -0.50
    roek
    -0.46
    newArrayList
    -0.45
    phosa
    -0.42
    httphttps
    -0.41
     []:
    -0.41
     Bly
    -0.41
    __.__
    -0.39
    SpringBootTest
    -0.39
     Financial
    -0.39
    POSITIVE LOGITS
     amizade
    0.53
     lunares
    0.51
     landmarks
    0.50
    +#+#
    0.50
     promoção
    0.48
    Misión
    0.47
     galore
    0.47
    ViewImports
    0.46
     landmark
    0.46
     PRIVACY
    0.46
    Activations Density 0.641%

    No Known Activations