© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 100001
    Prev
    Next
    INDEX
    Explanations

    phrases indicating engagement or interaction with the audience

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

    those interested in content

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     JpaRepository
    -0.45
    AutoField
    -0.45
    tvguidetime
    -0.43
     виправивши
    -0.39
     surla
    -0.37
    исленность
    -0.37
    Personensuche
    -0.36
    chutz
    -0.36
     متحده
    -0.36
    jay
    -0.35
    POSITIVE LOGITS
     readers
    0.71
     viewers
    0.69
     Zuschauer
    0.62
     readership
    0.62
     Publikum
    0.61
     lectores
    0.57
     audiences
    0.56
     reader
    0.55
    Readers
    0.55
     subscribers
    0.54
    Activations Density 0.133%

    No Known Activations