© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    references to food ingredients and health-related terms

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

    after prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    carrot celery

    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
    tvguidetime
    -0.61
    DebuggerNonUser
    -0.57
    atonin
    -0.53
    */
    -0.53
    ng
    -0.52
    pon
    -0.51
    ig
    -0.50
      
    -0.50
    gn
    -0.50
     porc
    -0.49
    POSITIVE LOGITS
    Datuak
    0.84
     vectorielles
    0.82
     beginnetje
    0.79
     propOrder
    0.79
     فريبيس
    0.75
     nahilalakip
    0.75
     ModelExpression
    0.74
     présidenti
    0.74
    IndentedString
    0.73
     Normdatei
    0.73
    Activations Density 0.016%

    No Known Activations