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. 12737
    Prev
    Next
    INDEX
    Explanations

    frequency markers and summary indicators in research findings

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

    Concluding or summarizing phrases

    np_acts-logits-general · gemini-2.0-flash

    finally, fourth, fifth, sixth, remaining

    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
     EconPapers
    -0.57
    complexContent
    -0.54
    ngdoc
    -0.54
    Życiorys
    -0.52
    gor
    -0.51
     leder
    -0.50
     APPELLATE
    -0.49
    __(/*!
    -0.49
    🚔
    -0.49
    sizeCache
    -0.49
    POSITIVE LOGITS
    Overall
    0.82
     Overall
    0.74
     Altogether
    0.72
     overall
    0.70
    gesamt
    0.69
    いかがでしたか
    0.69
    Summing
    0.68
     Insgesamt
    0.67
     以上
    0.66
     Ultimately
    0.66
    Activations Density 0.057%

    No Known Activations