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. 45
    Prev
    Next
    INDEX
    Explanations

    references to different sectors and industries, particularly in a financial or business context

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

    references to specific industries or sectors.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi

    business and industry-related terminology.

    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
     evacu
    -0.44
     scheduled
    -0.43
    OGND
    -0.40
     drafted
    -0.39
    Scheduled
    -0.39
     reten
    -0.39
     noodles
    -0.39
     ausge
    -0.38
     Scheduled
    -0.38
     smal
    -0.38
    POSITIVE LOGITS
     industry
    0.79
     settore
    0.79
    industry
    0.75
     sector
    0.75
     setor
    0.75
    業界
    0.71
    sector
    0.69
     indústria
    0.69
    SpringRunner
    0.68
     secteur
    0.68
    Activations Density 0.184%

    No Known Activations