Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7591
    Prev
    Next
    INDEX
    Explanations

    references to the atrocities and victims of war crimes and genocide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.65
     OFDb
    -0.61
     SEDS
    -0.58
     الرياضيه
    -0.58
     ladri
    -0.57
    Identyfik
    -0.54
     sockaddr
    -0.53
     angler
    -0.53
    Données
    -0.53
    unft
    -0.52
    POSITIVE LOGITS
     genocide
    1.30
     Genocide
    1.11
     genoc
    1.04
     Holocaust
    0.94
     massacre
    0.91
     massacres
    0.89
     atrocities
    0.87
     holocaust
    0.85
     extermination
    0.78
     atro
    0.76
    Activations Density 0.171%

    No Known Activations