© 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 EvalsExportsinterp-engineNEWAPI 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. 4079
    Prev
    Next
    INDEX
    Explanations

    decisions or actions related to cancelations and changes of plans

    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
    CodeAttribute
    -0.45
    bildeten
    -0.43
    DllImport
    -0.42
    demás
    -0.41
    secuencias
    -0.40
     avoient
    -0.40
    makeConstraints
    -0.39
     pinulongan
    -0.39
     antigüedad
    -0.38
    ɵɵelementEnd
    -0.38
    POSITIVE LOGITS
     cancelled
    0.92
     canceled
    0.91
     cancel
    0.90
     canceling
    0.81
     cancelling
    0.81
    cancel
    0.77
     cancellation
    0.77
     cancellations
    0.75
     rescin
    0.75
     Cancel
    0.74
    Activations Density 0.547%

    No Known Activations