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. 26792
    Prev
    Next
    INDEX
    Explanations

    mentions of demographic characteristics and data

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

    demographic

    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
    GEBURTSDATUM
    -0.57
     Portuguesa
    -0.47
     protoimpl
    -0.47
    \{\\
    -0.47
     المعيارى
    -0.46
    Enllaces
    -0.46
    URLConnection
    -0.45
     CURLOPT
    -0.45
    المناصب
    -0.45
    ritsar
    -0.44
    POSITIVE LOGITS
     demographic
    1.06
    Demographic
    0.93
     demographics
    0.91
     Demographic
    0.91
    demographic
    0.86
     Demographics
    0.85
    Demographics
    0.82
    DisplayMetrics
    0.64
     DEMO
    0.57
     demo
    0.57
    Activations Density 0.009%

    No Known Activations