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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 230
    Prev
    Next
    INDEX
    Explanations

    repeated references to "Big" related to the context of business or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.83
     AssemblyTitle
    -0.75
    autoreleasepool
    -0.74
     Hemisphere
    -0.73
    rungsseite
    -0.70
     Ambiental
    -0.65
    ://$
    -0.65
    LEncoder
    -0.65
    DockStyle
    -0.64
    تفصیلات
    -0.64
    POSITIVE LOGITS
     Big
    1.25
    Big
    1.13
    big
    0.96
     big
    0.90
     BIG
    0.79
    BIG
    0.78
    在大
    0.69
     大
    0.63
    到大
    0.62
    是小
    0.62
    Activations Density 0.144%

    No Known Activations