© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    references to upper and lower limits or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventId
    -0.68
    出版年
    -0.68
    SequentialGroup
    -0.66
    setVerticalGroup
    -0.66
    igurumi
    -0.64
     للمعارف
    -0.64
     Photocase
    -0.63
    addContainerGap
    -0.63
    nodoc
    -0.62
     prisms
    -0.62
    POSITIVE LOGITS
     upper
    1.32
     Upper
    1.26
     lower
    1.25
    Upper
    1.19
     Lower
    1.15
    Lower
    1.11
    upper
    1.10
     LOWER
    1.06
     UPPER
    1.04
    lower
    1.01
    Activations Density 0.264%

    No Known Activations