© 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. 23-GEMMASCOPE-RES-16K
    11. 9192
    Prev
    Next
    INDEX
    Explanations

    words related to employment contracts and terms of termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FailureListener
    -0.60
    nadier
    -0.58
    tagHelperRunner
    -0.58
    xrTableCell
    -0.56
    CppMethod
    -0.56
    ➟
    -0.56
    principalTable
    -0.55
    ViewFeatures
    -0.53
    
    -0.53
    iterranean
    -0.52
    POSITIVE LOGITS
     or
    0.66
     hoặc
    0.56
     или
    0.54
     또는
    0.50
    หรือ
    0.48
     vagy
    0.48
     voire
    0.47
     atau
    0.47
     alebo
    0.46
    或
    0.45
    Activations Density 0.691%

    No Known Activations