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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6046
    Prev
    Next
    INDEX
    Explanations

    terms related to diversity and representation in the context of Pacific Island cultures and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.57
    hånd
    -0.51
    ★★★★☆
    -0.49
     pleaſure
    -0.48
     ainfi
    -0.48
    TagMode
    -0.47
     myſelf
    -0.47
     Anſ
    -0.47
     auroit
    -0.47
     betweenstory
    -0.46
    POSITIVE LOGITS
    CppMethod
    0.43
    LabelTagHelper
    0.37
     disciplines
    0.37
     naj
    0.37
     species
    0.36
     ModelExpression
    0.36
     mus
    0.35
     other
    0.35
     κυ
    0.34
    المشاركات
    0.34
    Activations Density 1.222%

    No Known Activations