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. 5-GEMMASCOPE-RES-16K
    6. 13436
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to osteopathic and traditional medical practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réus
    -0.52
     comparação
    -0.50
    Fprintf
    -0.50
     skru
    -0.47
    Tembelea
    -0.46
     hí
    -0.46
     caller
    -0.45
    レージ
    -0.45
    bidity
    -0.45
     smokers
    -0.45
    POSITIVE LOGITS
     massage
    1.47
     Massage
    1.32
    Massage
    1.22
     massages
    1.21
    massage
    1.13
     acupuncture
    0.90
     masaj
    0.89
    按摩
    0.84
    マッサージ
    0.84
     Acupuncture
    0.82
    Activations Density 0.222%

    No Known Activations