© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83093
    Prev
    Next
    INDEX
    Explanations

    references to individuals in leadership or oversight roles within a project or study

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

    management and leadership roles

    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
    rungsseite
    -0.63
    Erreferentziak
    -0.60
     vermelhas
    -0.55
     escova
    -0.52
     mobiliario
    -0.50
     Winaray
    -0.48
    __(/*!
    -0.45
     downvoted
    -0.45
    Enllaces
    -0.45
     producten
    -0.45
    POSITIVE LOGITS
     Project
    0.57
     project
    0.55
     coordinator
    0.54
     managing
    0.51
    Project
    0.50
     director
    0.48
    ordinator
    0.48
     liaison
    0.47
    LookAnd
    0.47
     supervising
    0.46
    Activations Density 0.020%

    No Known Activations