© 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. 33-GEMMASCOPE-RES-16K
    11. 7474
    Prev
    Next
    INDEX
    Explanations

    terms related to cancellation and debt management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.49
    IsMutable
    -0.45
    Népesség
    -0.44
    AutoresizingMask
    -0.42
    WritableDatabase
    -0.41
    dafx
    -0.41
    addPreferredGap
    -0.40
    nloa
    -0.40
     Aging
    -0.40
     palio
    -0.40
    POSITIVE LOGITS
     cancel
    2.81
     cancellation
    2.72
     cancelled
    2.59
     canceled
    2.55
     cancelling
    2.44
     Cancel
    2.42
     cancels
    2.42
     cancellations
    2.41
     canceling
    2.39
    cancel
    2.34
    Activations Density 0.616%

    No Known Activations