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. 148
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and roles in legal contexts

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

    legal and transactional language related to property sales and legal proceedings.

    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
     his
    -0.49
     himself
    -0.46
     المعيارى
    -0.46
     sám
    -0.42
     Sünde
    -0.41
     yake
    -0.40
     singur
    -0.39
     kendisi
    -0.39
    himself
    -0.39
    是个
    -0.38
    POSITIVE LOGITS
     themselves
    1.08
    themselves
    1.00
    Their
    0.92
     yourselves
    0.92
     själva
    0.84
    their
    0.83
     Their
    0.79
     collectively
    0.78
     their
    0.75
    全員
    0.70
    Activations Density 0.634%

    No Known Activations