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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105840
    Prev
    Next
    INDEX
    Explanations

    specific references to antibacterial and cytotoxic effects on bacteria and cancer cells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    webElementXpaths
    -0.54
    RetentionPolicy
    -0.52
    CrossRef
    -0.44
     AttributeSet
    -0.44
     duele
    -0.42
    expandindo
    -0.38
     autorytatywna
    -0.38
    OpenHelper
    -0.38
     décisions
    -0.37
    fromCharCode
    -0.37
    POSITIVE LOGITS
    PreInfinity
    0.48
    minton
    0.47
     Champs
    0.46
     venice
    0.46
     Murch
    0.46
    ogaster
    0.45
     flocc
    0.44
    assay
    0.44
     Studios
    0.44
    pois
    0.44
    Activations Density 0.198%

    No Known Activations