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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14727
    Prev
    Next
    INDEX
    Explanations

    references to the length of time or duration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?\\
    -0.79
     chimiques
    -0.76
     Meksiku
    -0.75
    AccessFile
    -0.75
    INSEE
    -0.74
     ModelExpression
    -0.74
     ApJ
    -0.74
     ControllerBase
    -0.73
     @"";
    -0.73
     penny
    -0.73
    POSITIVE LOGITS
     duration
    1.34
    duration
    1.25
     durations
    1.16
    DURATION
    1.13
    Duration
    1.09
     Duration
    1.05
     DUR
    0.98
    setDuration
    0.92
     Durant
    0.85
     length
    0.81
    Activations Density 0.009%

    No Known Activations