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. 3006
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroprotection and immune responses

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

    preceding "protection" or forms of "protect."

    np_acts-logits-general · gemini-2.0-flash

    protection via conferred, offer, provide, shielded, guard

    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
    SuppressLint
    -0.50
    ⓧ
    -0.48
    mények
    -0.47
     GeoNames
    -0.44
    estream
    -0.42
     lanterna
    -0.40
    khana
    -0.40
    ้าย
    -0.40
    jsonPath
    -0.39
    npos
    -0.39
    POSITIVE LOGITS
     protection
    3.00
    protection
    2.57
     Protection
    2.54
     protect
    2.50
     protecting
    2.49
    Protection
    2.45
     protective
    2.38
     protections
    2.35
     protects
    2.34
     PROTECTION
    2.32
    Activations Density 0.572%

    No Known Activations