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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8573
    Prev
    Next
    INDEX
    Explanations

    phrases related to user experience improvement and environmental benefits

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

    Non-English text and numbers

    np_acts-logits-general · gemini-2.0-flash

    Waffles, polymerase complex

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates for text that follows a beginning-of-sentence marker, particularly focusing on formal, authoritative information presented in complete sentences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @au75
    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
    •Test list
    I don't know

    No Comments

    Negative Logits
     wherewith
    -0.69
    tvguidetime
    -0.63
    Totally
    -0.60
     awfully
    -0.59
     terribly
    -0.57
     Totally
    -0.56
     thingy
    -0.55
     geni
    -0.55
     bête
    -0.55
     terrific
    -0.54
    POSITIVE LOGITS
     تانيه
    0.82
    Geplaatst
    0.79
    بوابة
    0.78
     ligiloj
    0.78
    Билгалдахарш
    0.78
    💼
    0.76
    存于互联网档案馆
    0.75
    Collegamenti
    0.73
     propOrder
    0.73
     وتسجيلات
    0.72
    Activations Density 0.016%

    No Known Activations