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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15169
    Prev
    Next
    INDEX
    Explanations

    terms related to chronic pain and medical conditions

    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
    tagHelperRunner
    -0.62
    iconque
    -0.61
    printLine
    -0.58
    anskje
    -0.58
    出版年
    -0.57
     imprese
    -0.57
    OPSIS
    -0.56
    jdons
    -0.55
     apprentices
    -0.55
     yourselves
    -0.53
    POSITIVE LOGITS
     doctors
    1.25
    Doctors
    1.08
     Doctors
    1.01
    doctors
    0.91
     doctor
    0.89
     diagnosis
    0.84
     medication
    0.83
     diagnosed
    0.82
     dokter
    0.78
     medications
    0.78
    Activations Density 0.525%

    No Known Activations