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. 20-GEMMASCOPE-RES-16K
    6. 3032
    Prev
    Next
    INDEX
    Explanations

    numerical data or references to values and measurements

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

    Numbers followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    citations and numbers

    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
     two
    -0.60
     Two
    -0.56
    two
    -0.50
    Two
    -0.49
    def
    -0.49
     kedua
    -0.46
    два
    -0.46
    मान
    -0.45
    ❷
    -0.45
    的两
    -0.45
    POSITIVE LOGITS
    IUrlHelper
    0.93
     otomatig
    0.86
     Wallflower
    0.70
    ItemBackground
    0.68
    ngdoc
    0.68
    舺
    0.68
    ünst
    0.67
    TagMode
    0.65
    offsetof
    0.65
    tispiece
    0.65
    Activations Density 0.482%

    No Known Activations