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. 16-GEMMASCOPE-RES-16K
    6. 3131
    Prev
    Next
    INDEX
    Explanations

    conditions related to optimization and efficiency in processes

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

    Transition or start of a process

    np_acts-logits-general · gemini-2.0-flash

    point after which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.57
     estekak
    -0.53
     repose
    -0.52
     Ruhe
    -0.51
    ennent
    -0.51
     kasarigan
    -0.51
     gql
    -0.51
    withstanding
    -0.51
     attesa
    -0.48
    ׁ
    -0.48
    POSITIVE LOGITS
     becomes
    0.86
     begins
    0.83
     начинает
    0.78
     zaczyna
    0.78
     mulai
    0.75
     begint
    0.74
     commencent
    0.73
     devient
    0.73
    Beyond
    0.72
    もはや
    0.71
    Activations Density 0.484%

    No Known Activations