Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 10980
    Prev
    Next
    INDEX
    Explanations

    terms related to tax returns and income reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.81
    EndInit
    -0.77
     <=",
    -0.75
    BeginInit
    -0.73
    MemoryWarning
    -0.73
    principalColumn
    -0.71
    ArgsConstructor
    -0.70
    tagHelperRunner
    -0.69
    HtmlAttribute
    -0.68
    IUrlHelper
    -0.65
    POSITIVE LOGITS
     tax
    1.57
     Tax
    1.41
    Tax
    1.31
    tax
    1.25
     TAX
    1.13
    TAX
    1.08
     IRS
    1.07
     taxable
    1.07
     taxes
    1.07
     taxpayers
    0.99
    Activations Density 0.396%

    No Known Activations