© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 152
    Prev
    Next
    INDEX
    Explanations

    references to years of experience and expertise in various fields

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

    "experience"

    np_acts-logits-general · gemini-2.0-flash

    experienced individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     jScrollPane
    -0.54
    DataAnnotations
    -0.52
     الحره
    -0.50
    featureID
    -0.49
    setVerticalGroup
    -0.48
    mybatisplus
    -0.48
    (!__
    -0.46
     initComponents
    -0.46
    msgTypes
    -0.46
    ulemon
    -0.45
    POSITIVE LOGITS
    experienced
    0.84
     experienced
    0.84
    Experienced
    0.81
     Experienced
    0.75
    经验
    0.74
     experience
    0.73
    Experience
    0.72
     veteran
    0.71
    EXPERIENCE
    0.70
     expérimentés
    0.69
    Activations Density 0.191%

    No Known Activations