© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    terms related to deputy or assistant administrative positions

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

    preceding titles/positions

    np_acts-logits-general · gemini-2.0-flash

    deputy and assistant titles

    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
    IntoConstraints
    -0.74
    forName
    -0.73
    featureID
    -0.61
    bcryptjs
    -0.58
    cshtml
    -0.58
    contentValues
    -0.58
    orianCalendar
    -0.57
    URLException
    -0.56
    Morrison
    -0.56
    urlopen
    -0.55
    POSITIVE LOGITS
     deputy
    0.64
     assistant
    0.63
     Deputy
    0.59
    PUTY
    0.59
     Vice
    0.57
     vice
    0.57
     Assistant
    0.53
     fellow
    0.53
     chief
    0.49
    Vice
    0.49
    Activations Density 0.181%

    No Known Activations