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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 39005
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to statistics and probability theory

    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
    Према
    -0.50
    SequentialGroup
    -0.50
     kiệm
    -0.49
     مشين
    -0.48
    AddTagHelper
    -0.46
    ToScroll
    -0.46
    மே
    -0.45
    InSection
    -0.44
    SPATH
    -0.44
    存于互联网档案馆
    -0.43
    POSITIVE LOGITS
    Autoritní
    0.77
     Administrativna
    0.47
    mathbf
    0.41
    ContentAlignment
    0.39
     betweenstory
    0.37
     AssemblyTitle
    0.36
    UrlResolution
    0.36
    CppMethod
    0.35
     JAXBElement
    0.34
    ledem
    0.33
    Activations Density 0.085%

    No Known Activations