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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7116
    Prev
    Next
    INDEX
    Explanations

    references to richness and depth in various contexts, particularly culture, history, and biodiversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    application
    -0.57
    action
    -0.52
     action
    -0.49
     Stevenson
    -0.49
    MoveTo
    -0.48
    BaseModel
    -0.45
    apply
    -0.45
    krie
    -0.45
     Mosley
    -0.45
     application
    -0.44
    POSITIVE LOGITS
    riched
    0.90
    richment
    0.81
     wealth
    0.77
     Riches
    0.76
     richness
    0.74
     Wealth
    0.72
    rich
    0.71
     rich
    0.70
     richesse
    0.69
     riqueza
    0.69
    Activations Density 0.237%

    No Known Activations