© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4829
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cold" and its association with violence or killing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pact
    -0.50
     topic
    -0.49
     Refuge
    -0.48
    
    -0.46
    ✷
    -0.46
    AdapterView
    -0.46
    IsContent
    -0.45
     Topic
    -0.45
    <%@
    -0.44
     Amity
    -0.43
    POSITIVE LOGITS
     killing
    0.94
     killed
    0.93
     Killing
    0.89
    killed
    0.88
    killing
    0.87
    Killing
    0.86
     cold
    0.82
     Killed
    0.79
     kill
    0.77
     KILL
    0.75
    Activations Density 0.074%

    No Known Activations