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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5910
    Prev
    Next
    INDEX
    Explanations

    references to violence and persecution during wartime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    concentration camps and genocide

    np_acts-logits-general · gemini-2.0-flash

    Holocaust and concentration camp victims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.67
     الرياضيه
    -0.64
    GEBURTSDATUM
    -0.61
     Weib
    -0.61
     Spearman
    -0.59
    octanol
    -0.58
     تانيه
    -0.57
    Identyfik
    -0.56
    hilterra
    -0.53
     Sitten
    -0.52
    POSITIVE LOGITS
     genocide
    1.24
     Holocaust
    1.12
     victims
    1.06
     genoc
    1.04
     Genocide
    1.03
     survivors
    1.02
     survivor
    1.02
     atrocities
    1.00
     atro
    0.97
     massacre
    0.95
    Activations Density 0.254%

    No Known Activations