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. 2-GEMMASCOPE-RES-16K
    6. 6290
    Prev
    Next
    INDEX
    Explanations

    the concept of wealth or richness, particularly in a figurative or qualitative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bernadette
    -0.70
     Barnabas
    -0.70
    Manbalar
    -0.67
     reformation
    -0.65
     <=",
    -0.62
    soort
    -0.62
     Gaulle
    -0.62
     papillon
    -0.61
     Stampa
    -0.61
     Athene
    -0.60
    POSITIVE LOGITS
     rich
    3.71
     Rich
    3.23
    rich
    3.17
    Rich
    3.14
     RICH
    2.99
     richer
    2.72
    RICH
    2.69
     richness
    2.46
     richest
    2.42
     riche
    2.30
    Activations Density 0.055%

    No Known Activations