© 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. 3-GEMMASCOPE-RES-16K
    11. 8530
    Prev
    Next
    INDEX
    Explanations

    references to duration in various contexts

    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
    awtextra
    -0.42
    NewReader
    -0.40
    SpringRunner
    -0.39
     Lerner
    -0.39
     unmistakable
    -0.35
     initComponents
    -0.35
    思い
    -0.34
    })->
    -0.34
    存于互联网档案馆
    -0.33
     unusual
    -0.32
    POSITIVE LOGITS
     duration
    0.96
     Duration
    0.93
    Duration
    0.86
    duration
    0.84
     durations
    0.83
     Dur
    0.80
    Dur
    0.79
     DUR
    0.79
    dur
    0.78
     dur
    0.77
    Activations Density 0.053%

    No Known Activations