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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 16190
    Prev
    Next
    INDEX
    Explanations

    references to heaven and concepts associated with it, such as forgiveness and paradise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.74
     للمعارف
    -0.70
    RequestMapping
    -0.69
    illoma
    -0.58
     onResponse
    -0.58
     AspNetCore
    -0.57
     WebDriverWait
    -0.55
    intenant
    -0.55
     Rump
    -0.54
    ğinde
    -0.54
    POSITIVE LOGITS
     heaven
    1.09
     Heaven
    1.05
     badly
    0.97
    heaven
    0.95
     Paradise
    0.95
     paradise
    0.93
    Heaven
    0.86
    Paradise
    0.85
     HEAVEN
    0.84
     necessity
    0.80
    Activations Density 0.100%

    No Known Activations