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. 2357
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental damage and health risks associated with UV radiation

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

    Protection from sun/UV exposure

    np_acts-logits-general · gemini-2.0-flash

    sun protection

    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
     abscess
    -0.57
    awaiter
    -0.56
    pensione
    -0.55
     botines
    -0.55
     Ack
    -0.53
     arranque
    -0.52
     amnesty
    -0.52
     Freight
    -0.51
    entil
    -0.51
    YNAMICS
    -0.51
    POSITIVE LOGITS
     sun
    1.69
     sunscreen
    1.46
     Sun
    1.43
    Sun
    1.42
     sunburn
    1.34
    sun
    1.34
     SUN
    1.25
     Sunscreen
    1.21
    Suns
    1.20
     SPF
    1.19
    Activations Density 0.098%

    No Known Activations