© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6964
    Prev
    Next
    INDEX
    Explanations

    references to coding standards and error handling in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <tfoot>
    -0.34
     passing
    -0.31
     result
    -0.28
     benefit
    -0.28
     サムネイル
    -0.28
     معمول
    -0.28
     passage
    -0.26
    ǔ
    -0.26
    集
    -0.26
     management
    -0.26
    POSITIVE LOGITS
    :✨
    9.94
     EconPapers
    1.41
    ✨:
    1.27
     autorytatywna
    1.26
     surla
    1.21
    msgTypes
    1.16
    GEBURTSDATUM
    1.15
    Rüyada
    1.11
     nahilalakip
    1.09
    Personendaten
    1.09
    Activations Density 0.019%

    No Known Activations