© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 14225
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to bacteria, particularly those that are pathogenic or involved in infection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taminophen
    -0.60
     voulons
    -0.60
    himovic
    -0.59
    clerosis
    -0.53
     remar
    -0.53
    理石
    -0.52
     betweenstory
    -0.52
     تضيفلها
    -0.51
    ondissement
    -0.50
     Lus
    -0.49
    POSITIVE LOGITS
     bacteria
    1.32
     bacterial
    1.21
    Bacteria
    1.14
     Bacteria
    1.13
     Bacterial
    1.11
    Bacterial
    1.06
    bacterial
    1.02
     bacterium
    1.02
     microbial
    1.00
    bacteria
    1.00
    Activations Density 1.281%

    No Known Activations