Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15471
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structures, particularly in the context of coding and software development

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

    Followed by Roman numerals or numbers

    np_acts-logits-general · gemini-2.0-flash

    numbered parts or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.85
     للمعارف
    -0.83
    ChildScrollView
    -0.82
    下载附件
    -0.82
    Vidite
    -0.75
    SequentialGroup
    -0.73
     AssemblyCulture
    -0.73
     JpaRepository
    -0.71
    Lähteet
    -0.67
    NewUrlParser
    -0.67
    POSITIVE LOGITS
     II
    1.53
     III
    1.47
     #
    1.20
    III
    1.17
     IV
    1.14
    II
    1.07
     VII
    1.04
    1
    1.03
     VIII
    0.98
     \#
    0.98
    Activations Density 2.685%

    No Known Activations