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. 7754
    Prev
    Next
    INDEX
    Explanations

    terms related to antimicrobial effects and substances influencing microbial activity

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

    Antimicrobial or antibacterial activity

    np_acts-logits-general · gemini-2.0-flash

    antibacterial activity against bacteria

    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
    +#+#
    -0.83
     MainAxisSize
    -0.81
     Signalez
    -0.71
    MigrationBuilder
    -0.69
     <=",
    -0.66
    HttpPut
    -0.66
     فريبيس
    -0.66
     IBOutlet
    -0.65
    windowFixed
    -0.64
     JFK
    -0.64
    POSITIVE LOGITS
     bacteria
    1.59
     bacterial
    1.42
     microorganisms
    1.30
     bacterium
    1.29
     microbes
    1.26
     microbial
    1.25
     Bacteria
    1.24
    bacteria
    1.17
    Bacteria
    1.13
     Bacterial
    1.11
    Activations Density 0.996%

    No Known Activations