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. 20-GEMMASCOPE-RES-16K
    6. 2282
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and conditions, particularly related to studies and outcomes

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

    Followed or preceded by a mathematical or technical term

    np_acts-logits-general · gemini-2.0-flash

    technical and procedural concepts

    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-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
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.75
     ddelweddau
    -0.74
    RegressionTest
    -0.74
    IVEREF
    -0.71
    elemField
    -0.67
    ThroughAttribute
    -0.67
     lenker
    -0.63
     Infórmanos
    -0.63
    :✨
    -0.62
     CreateTagHelper
    -0.61
    POSITIVE LOGITS
     we
    1.97
     they
    1.88
     there
    1.77
     it
    1.50
     you
    1.42
     he
    1.30
     فإن
    1.27
     они
    1.27
    there
    1.25
    they
    1.23
    Activations Density 2.248%

    No Known Activations