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. 15982
    Prev
    Next
    INDEX
    Explanations

    terms related to programming data structures and legal terminology regarding discrimination and credit applications

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

    after optional/packed/underscore

    np_acts-logits-general · gemini-2.0-flash

    optional packed bool string

    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
    tagHelperRunner
    -0.83
    PerformLayout
    -0.73
    imageshack
    -0.55
     Вікіпе
    -0.55
    DockStyle
    -0.53
     AspNetCore
    -0.49
     Himo
    -0.48
     مشارکت‌کنندگان
    -0.47
     tigre
    -0.47
     CreateTagHelper
    -0.46
    POSITIVE LOGITS
    onViewCreated
    0.75
    出版年
    0.75
     betweenstory
    0.70
    osoba
    0.62
    يكب
    0.60
     utafitiHapana
    0.60
    ELTS
    0.60
    #+#
    0.59
    brainly
    0.58
     StatefulWidget
    0.58
    Activations Density 0.362%

    No Known Activations