© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 52569
    Prev
    Next
    INDEX
    Explanations

    instances of time or date-related variables

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

    start time or stiffness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eql
    -0.45
    quelize
    -0.45
    mouseleave
    -0.43
    beelding
    -0.38
    ỡng
    -0.37
     informée
    -0.36
    fputs
    -0.35
    DataAnnotations
    -0.34
    ContainsKey
    -0.34
     NoSuch
    -0.34
    POSITIVE LOGITS
     startTime
    2.25
    startTime
    2.19
    StartTime
    1.95
    starttime
    1.24
    StartDate
    0.98
     startDate
    0.98
     STARTED
    0.98
     started
    0.97
     starting
    0.95
    started
    0.94
    Activations Density 0.001%

    No Known Activations