© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11363
    Prev
    Next
    INDEX
    Explanations

    terms related to materials science and applications in medical or dental fields

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

    Polymer, molecular weight, or resin

    np_acts-logits-general · gemini-2.0-flash

    polymer molecular weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferru
    -0.54
    ธ
    -0.53
    autoFocus
    -0.53
    imeni
    -0.52
    CUSSION
    -0.52
     Btu
    -0.51
     المعيارى
    -0.50
    medriver
    -0.49
     Bradshaw
    -0.48
     Çe
    -0.48
    POSITIVE LOGITS
     polymer
    1.00
     Polymer
    0.91
     polymers
    0.89
     Polymers
    0.88
     copolymer
    0.86
    Polymer
    0.84
    polymer
    0.83
     polymeric
    0.76
     monomer
    0.75
     monomers
    0.74
    Activations Density 0.765%

    No Known Activations