Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 68222
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to mathematical functions and operations

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

    math calculations with respect to

    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
    elemField
    -0.56
     Paglinawan
    -0.54
    RegistryLite
    -0.44
    transQ
    -0.39
    msgTypes
    -0.37
     forState
    -0.36
    richTextPanel
    -0.34
    ArrowToggle
    -0.34
    ंदीखरीदारी
    -0.33
    meteries
    -0.32
    POSITIVE LOGITS
    Története
    0.55
    autoreleasepool
    0.53
     SafeMath
    0.50
    HasAnnotation
    0.49
    acus
    0.48
    DATAS
    0.46
    مصادر
    0.45
    sum
    0.45
    solu
    0.44
    serv
    0.43
    Activations Density 0.022%

    No Known Activations