© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12819
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial penalties in a tax context

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

    legal and financial terminology related to penalties, taxes, and regulatory compliance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Daß
    -0.72
     flavorful
    -0.69
    BeginInit
    -0.67
     للمعارف
    -0.66
     أيضاً
    -0.64
     ๆ
    -0.63
     mußten
    -0.61
    FAVOR
    -0.60
     colorful
    -0.60
     și
    -0.60
    POSITIVE LOGITS
     Australian
    1.26
     Queensland
    1.21
     Australia
    1.20
    Australian
    1.17
     Melbourne
    1.14
     Brisbane
    1.14
     CSIRO
    1.13
     Australians
    1.13
     Pty
    1.10
    Australia
    1.09
    Activations Density 0.734%

    No Known Activations