© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9291
    Prev
    Next
    INDEX
    Explanations

    references to the act of closing or finalizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➽
    -0.40
    CppMethod
    -0.37
    toolTip
    -0.37
     valueForKey
    -0.37
    menuStrip
    -0.36
     AssemblyProduct
    -0.36
    yticks
    -0.35
    führer
    -0.35
    arry
    -0.35
    ativement
    -0.35
    POSITIVE LOGITS
     closing
    3.63
     Closing
    3.42
    Closing
    3.22
    closing
    3.19
     closes
    3.09
     closure
    2.88
     closed
    2.86
     clos
    2.72
     Closes
    2.70
     Closure
    2.61
    Activations Density 0.124%

    No Known Activations