© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    keywords and variations related to leadership and guiding roles

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

    Sentences containing the word "lead" or "led"

    np_acts-logits-general · gemini-2.0-flash

    leading or conducting

    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
    NonQuery
    -0.47
     complicated
    -0.42
     bagay
    -0.41
    quilo
    -0.41
     compartment
    -0.41
     kanyang
    -0.40
     museum
    -0.40
     vong
    -0.40
     vacation
    -0.40
     Hutchinson
    -0.39
    POSITIVE LOGITS
    Lead
    1.24
    lead
    1.22
     Lead
    1.21
     LEAD
    1.16
     lead
    1.15
    Leads
    1.13
    leads
    1.13
    leading
    1.09
    LEAD
    1.09
    Leading
    1.07
    Activations Density 0.084%

    No Known Activations