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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7154
    Prev
    Next
    INDEX
    Explanations

    references to radiation dosage and its effects in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kespea
    -0.62
    Життєпис
    -0.60
     ujednoznacz
    -0.59
     RouterModule
    -0.58
    الحياه
    -0.58
    quelize
    -0.58
     Lubric
    -0.58
     Elasticity
    -0.57
    SourceChecksum
    -0.57
     EconPapers
    -0.57
    POSITIVE LOGITS
     radiation
    1.43
     Radiation
    1.26
    Radiation
    1.22
     radio
    1.13
     Radio
    1.12
    radiation
    1.12
     RADIATION
    1.11
    radio
    1.09
     radioactive
    1.09
     radioactivity
    1.07
    Activations Density 0.522%

    No Known Activations