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. 12-GEMMASCOPE-RES-16K
    6. 4665
    Prev
    Next
    INDEX
    Explanations

    references to taxation and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lolita
    -0.83
    phrine
    -0.81
    ✨:
    -0.81
    singleton
    -0.78
    andidate
    -0.74
    noin
    -0.72
    mobileqq
    -0.72
     compréhen
    -0.71
    WaitGroup
    -0.71
     trit
    -0.71
    POSITIVE LOGITS
     tax
    1.82
     taxes
    1.78
     TAX
    1.68
     Tax
    1.67
    Taxes
    1.64
     Taxes
    1.61
    tax
    1.56
    Tax
    1.50
    TAX
    1.48
    taxes
    1.42
    Activations Density 0.045%

    No Known Activations