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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 14004
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to political repression and violence

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

    World War II concentration camps/authorities

    np_acts-logits-general · gemini-2.0-flash

    Nazi concentration camps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.74
     &___
    -0.68
    Geplaatst
    -0.60
     CURIAM
    -0.57
    AddHtmlAttribute
    -0.57
    ExecuteReader
    -0.56
     beginnetje
    -0.51
    mishes
    -0.49
     Albany
    -0.47
     Martine
    -0.47
    POSITIVE LOGITS
     SS
    0.91
     Nazi
    0.86
     Hitler
    0.82
     NSD
    0.76
     Gesta
    0.74
     concentration
    0.71
     Nazis
    0.70
     Reich
    0.69
    Nazi
    0.68
    Hitler
    0.68
    Activations Density 0.294%

    No Known Activations