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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 97
    Prev
    Next
    INDEX
    Explanations

    terms related to insurance coverage and financial obligations

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

    Tax exclusions or exemptions

    np_acts-logits-general · gemini-2.0-flash

    qualified principal residence indebtedness exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    تقاوى
    -0.55
    endphp
    -0.51
     outsourcing
    -0.50
    Remind
    -0.48
     SWOT
    -0.48
    ResumeLayout
    -0.48
     TType
    -0.48
    BoxShadow
    -0.48
    Билгалдахарш
    -0.48
     Remind
    -0.47
    POSITIVE LOGITS
     eligible
    0.94
     qualifying
    0.86
    eligible
    0.85
     eligibility
    0.79
    Eligible
    0.74
     elig
    0.72
    WithIOException
    0.71
     Eligible
    0.68
     Qualifying
    0.67
     qualify
    0.67
    Activations Density 0.480%

    No Known Activations