© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2132
    Prev
    Next
    INDEX
    Explanations

    terms related to the Holocaust and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.61
     متعلقه
    -0.60
     الحره
    -0.58
    GEBURTSDATUM
    -0.56
    Identyfik
    -0.55
     vedette
    -0.54
    octanol
    -0.52
     referenties
    -0.52
     angler
    -0.51
     angling
    -0.49
    POSITIVE LOGITS
     genocide
    1.26
     Holocaust
    1.17
     atrocities
    1.07
     victims
    1.07
     Genocide
    1.04
     survivor
    1.03
     atro
    1.00
     genoc
    1.00
     survivors
    0.99
     holocaust
    0.98
    Activations Density 0.264%

    No Known Activations