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. 8-GEMMASCOPE-RES-16K
    6. 7596
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and well-wishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leksikon
    -0.80
    richTextPanel
    -0.76
     translateY
    -0.73
    Carthy
    -0.69
     SAC
    -0.68
    CharField
    -0.67
    rootDir
    -0.66
     ویکی‌آمباردا
    -0.65
    Rodriguez
    -0.64
     Dreyfus
    -0.64
    POSITIVE LOGITS
     HOPE
    1.77
     hopes
    1.68
     hope
    1.65
    HOPE
    1.63
    hope
    1.62
     Hopes
    1.58
     Hope
    1.57
    Hope
    1.51
     hoped
    1.42
     hoping
    1.33
    Activations Density 0.041%

    No Known Activations