© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 15164
    Prev
    Next
    INDEX
    Explanations

    references to ethnic groups and events related to victimization or persecution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owników
    -0.60
    \"]
    -0.59
     Stability
    -0.57
     Ibarra
    -0.56
     stabilité
    -0.55
     stability
    -0.55
     Dhoni
    -0.55
     Molière
    -0.55
     stabilize
    -0.53
     estabilidad
    -0.52
    POSITIVE LOGITS
     Holocaust
    0.90
    locaust
    0.81
     holocaust
    0.77
     Auschwitz
    0.74
     genocide
    0.73
     genoc
    0.71
     survivor
    0.68
     survivors
    0.65
     extermination
    0.65
     sobrevi
    0.64
    Activations Density 0.074%

    No Known Activations