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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10120
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to progress or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    positive sentiment/improvement

    np_acts-logits-general · gemini-2.0-flash

    future, proved, more, need, strengthen, enhance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.67
    queryInterface
    -0.56
     nakalista
    -0.56
     nacht
    -0.54
     Autorisations
    -0.52
    
    -0.52
    
    -0.51
    RTGC
    -0.50
     mistakenly
    -0.50
    PropertyChanging
    -0.49
    POSITIVE LOGITS
    ITURE
    0.42
     improved
    0.41
     favorable
    0.40
     productive
    0.39
    :✨
    0.36
    SuspendLayout
    0.36
    emlrt
    0.35
     spi
    0.35
    xsl
    0.35
     pono
    0.35
    Activations Density 0.045%

    No Known Activations