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

    terms related to richness and abundance in various contexts

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

    the word "rich" in descriptive contexts about history, culture, or experience.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    The term "rich" frequently appears to describe abundance, depth, or quality across diverse contexts, including culture, history, and biodiversity. It is used to convey a sense of value and significance in various narratives.

    eleuther_acts_top20 · gpt-4o-miniTriggered by @neilrathi

    references to richness in the context of culture, history, or resources.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    application
    -0.64
     application
    -0.53
     Motorola
    -0.50
    krie
    -0.49
     Mosley
    -0.48
    action
    -0.47
    LookAnd
    -0.47
     phasing
    -0.47
     Halliday
    -0.47
     calipers
    -0.46
    POSITIVE LOGITS
    riched
    0.96
    richment
    0.82
     rich
    0.81
    Rich
    0.80
    RICH
    0.79
     richness
    0.79
    rich
    0.78
     Rich
    0.77
     RICH
    0.77
     richesse
    0.74
    Activations Density 0.121%

    No Known Activations