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. 30249
    Prev
    Next
    INDEX
    Explanations

    words related to language proficiency and communication barriers

    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
     surla
    -0.60
    GeneratedValue
    -0.59
     AssemblyCompany
    -0.57
    RenderAtEndOf
    -0.56
     StatefulWidget
    -0.54
    AsUp
    -0.54
    WithIOException
    -0.53
    IBAction
    -0.52
    ValueGenerated
    -0.52
    AddTagHelper
    -0.50
    POSITIVE LOGITS
     language
    0.76
     Language
    0.69
    Language
    0.69
     languages
    0.65
    language
    0.65
     dialects
    0.59
     linguistic
    0.59
     Languages
    0.58
     Sprach
    0.58
     idioma
    0.56
    Activations Density 0.052%

    No Known Activations