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. 16-GEMMASCOPE-RES-16K
    6. 11939
    Prev
    Next
    INDEX
    Explanations

    key individuals and organizations related to a specific narrative or context

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

    Irish-Catholic people/culture

    np_acts-logits-general · gemini-2.0-flash

    Irish Catholic gangster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.74
    
    -0.71
    errHandler
    -0.62
    mentaux
    -0.59
    لينكات
    -0.58
     تضيفلها
    -0.57
     tartalomajánló
    -0.57
    astéro
    -0.57
    يميديا
    -0.56
     aman
    -0.55
    POSITIVE LOGITS
     Catholic
    1.08
    Catholic
    0.99
     catholic
    0.83
     Catholics
    0.83
    catholic
    0.81
     Catholicism
    0.78
     católica
    0.74
     Irish
    0.71
     Hiber
    0.69
     katholischen
    0.68
    Activations Density 0.189%

    No Known Activations