© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12279
    Prev
    Next
    INDEX
    Explanations

    references to administrative functions in a programming or software context

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

    admin ui editor code

    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
     '\\;'
    -0.57
    thâu
    -0.50
    URLException
    -0.47
     transfieras
    -0.47
     QtCore
    -0.47
     zijne
    -0.45
    !*\
    -0.45
    TintMode
    -0.44
    HasAnnotation
    -0.43
    ="@+
    -0.42
    POSITIVE LOGITS
    ModelAdmin
    1.31
     admin
    0.72
    Admin
    0.71
     Admin
    0.69
    admin
    0.66
     ADMIN
    0.60
     administ
    0.59
     Administ
    0.58
     administer
    0.57
     administra
    0.57
    Activations Density 0.001%

    No Known Activations