© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12659
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to authority, submission, and hierarchical dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     surla
    -0.60
    瘍
    -0.46
     الرياضيه
    -0.45
    cinogenicity
    -0.44
    Carex
    -0.42
    zarchiwizowane
    -0.42
    habhar
    -0.41
    migrationBuilder
    -0.40
     <>",
    -0.40
     whereof
    -0.39
    POSITIVE LOGITS
     submissive
    0.70
     subordinate
    0.64
     meek
    0.62
     subserv
    0.62
     subordination
    0.60
     obedient
    0.54
     surrender
    0.53
     obedience
    0.50
    obey
    0.50
     Dependence
    0.50
    Activations Density 0.257%

    No Known Activations