© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 510
    Prev
    Next
    INDEX
    Explanations

    references to "contact" in various contexts, particularly relating to contact lenses and contact angles

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

    terms related to contact angles in scientific contexts

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

    contact angle

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    httphttps
    -0.74
    Millisecond
    -0.60
     Schülern
    -0.58
    ậy
    -0.58
    ḫ
    -0.58
     ràng
    -0.57
    éről
    -0.56
    hood
    -0.56
    فاده
    -0.56
    сылкі
    -0.56
    POSITIVE LOGITS
     pinulongan
    0.96
     Contacts
    0.81
    Contacts
    0.73
     contacts
    0.73
    ually
    0.71
    contacts
    0.69
     CONTACT
    0.66
     Contact
    0.64
     lenses
    0.64
    ual
    0.62
    Activations Density 0.029%

    No Known Activations