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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6502
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.48
     falls
    -0.46
    ToMove
    -0.45
     bergerak
    -0.44
     of
    -0.43
    ichè
    -0.42
     variables
    -0.42
    JpaRepository
    -0.41
     plus
    -0.40
    totals
    -0.40
    POSITIVE LOGITS
    TagMode
    0.89
    CloseOperation
    0.86
     createSlice
    0.79
    Портал
    0.78
     useAppContext
    0.75
    WithIOException
    0.74
    InjectAttribute
    0.74
    تقاوى
    0.74
    runApp
    0.73
    PMailer
    0.72
    Activations Density 0.660%

    No Known Activations