© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2423
    Prev
    Next
    INDEX
    Explanations

    references to status properties in entity management systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    status or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     '\\;'
    -0.46
     Exacts
    -0.42
     aDecoder
    -0.42
     nonUne
    -0.42
    OrNil
    -0.41
     CreateTagHelper
    -0.40
    anthene
    -0.39
    发表于
    -0.37
    ÉE
    -0.37
    Ӕ
    -0.35
    POSITIVE LOGITS
     status
    1.61
     statuses
    1.47
     Status
    1.41
    Status
    1.37
    status
    1.35
    状态
    1.27
     getStatus
    1.26
     STATUS
    1.23
     상태
    1.20
     estatus
    1.20
    Activations Density 0.088%

    No Known Activations