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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 26782
    Prev
    Next
    INDEX
    Explanations

    references to Jewish history and the Holocaust

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

    Holocaust, Jews, camps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    URLException
    -0.71
     فريبيس
    -0.63
    GEBURTS
    -0.57
    windowFixed
    -0.56
     CreateTagHelper
    -0.55
    AnchorStyles
    -0.55
    styleType
    -0.54
    Rüyada
    -0.52
    MessageTagHelper
    -0.51
    adget
    -0.51
    POSITIVE LOGITS
    locaust
    0.66
     Holocaust
    0.60
     Jewish
    0.60
     Jews
    0.54
    Jewish
    0.52
     holocaust
    0.48
     Nazis
    0.44
     Nazi
    0.44
     nazis
    0.43
     jewish
    0.41
    Activations Density 0.046%

    No Known Activations