© 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. 33-GEMMASCOPE-RES-16K
    11. 5740
    Prev
    Next
    INDEX
    Explanations

    terms related to incidents or events that occur, particularly in contexts of injury or legal matters

    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
     CreateTagHelper
    -0.65
    wiſe
    -0.64
     Kebijakan
    -0.56
    ſelves
    -0.55
     Inscrivez
    -0.55
    征詢我
    -0.53
     StatefulWidget
    -0.53
    resizingMask
    -0.52
    NUMX
    -0.50
    RTDA
    -0.50
    POSITIVE LOGITS
     Incident
    0.51
     inc
    0.50
     incident
    0.47
     scene
    0.46
     involving
    0.45
     incidents
    0.44
     occurring
    0.43
     Occur
    0.43
     occurrence
    0.43
     Inc
    0.42
    Activations Density 0.248%

    No Known Activations