© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2237
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldOffsetTable
    -0.36
    >>()
    -0.36
    ).__
    -0.34
    */),
    -0.32
    oredCriteria
    -0.31
    "),
    -0.30
    CreateModel
    -0.29
    PropertyChanging
    -0.28
     explí
    -0.28
    imi
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.75
     nahilalakip
    0.71
    ValueStyle
    0.65
    Tikang
    0.58
     OFDb
    0.56
    farwyddwr
    0.56
    Soorten
    0.54
    出版年
    0.54
     يتيمه
    0.54
    transQ
    0.52
    Activations Density 1.272%

    No Known Activations