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. 15858
    Prev
    Next
    INDEX
    Explanations

    references to processes or actions involving effort or development

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

    after "to" (often verbs)

    np_acts-logits-general · gemini-2.0-flash

    bringing to fruition

    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
     future
    -0.63
    ếm
    -0.52
    AddHtmlAttribute
    -0.52
    予定です
    -0.51
    future
    -0.51
    usehen
    -0.51
     futuro
    -0.48
    página
    -0.47
     zukünf
    -0.47
     künftig
    -0.47
    POSITIVE LOGITS
     this
    0.83
    脚注の使い方
    0.79
    تقاوى
    0.77
    this
    0.77
    principalColumn
    0.72
    الإنجليزية
    0.71
    这份
    0.61
    才
    0.61
    才有
    0.60
    而成
    0.59
    Activations Density 0.283%

    No Known Activations