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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30493
    Prev
    Next
    INDEX
    Explanations

    references to Project Object Model (POM) in software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     مشين
    -1.60
     Wikimedijinoj
    -1.36
    出版年
    -1.14
    DockStyle
    -0.76
     ujednoznacz
    -0.75
    verifyException
    -0.68
     EClass
    -0.65
     betweenstory
    -0.65
    expandindo
    -0.64
     виправивши
    -0.64
    POSITIVE LOGITS
    Données
    2.39
    setHorizontal
    0.81
    Général
    0.63
     clés
    0.61
     générales
    0.52
    Caractéristiques
    0.49
    Lähteet
    0.45
     Fassung
    0.44
     Données
    0.43
    ponses
    0.42
    Activations Density 0.000%

    No Known Activations