Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14656
    Prev
    Next
    INDEX
    Explanations

    references to antimicrobial properties and responses in immune function

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

    Antimicrobial or antibacterial properties/substances

    np_acts-logits-general · gemini-2.0-flash

    antimicrobial substances and killing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.69
    IntoConstraints
    -0.68
     Ptole
    -0.59
     Hima
    -0.58
    TERY
    -0.58
    fromnode
    -0.57
    MockBean
    -0.55
     disambiguazione
    -0.55
    dération
    -0.55
     constipation
    -0.54
    POSITIVE LOGITS
     kill
    1.19
     kills
    1.15
     killing
    1.11
    kills
    0.95
    killing
    0.95
    kill
    0.94
     Kills
    0.92
     antiviral
    0.91
     disinf
    0.90
     disinfect
    0.89
    Activations Density 0.762%

    No Known Activations