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. 2750
    Prev
    Next
    INDEX
    Explanations

    instances of important numerical data or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    setupUi
    -0.67
    SpringRunner
    -0.65
     насељу
    -0.62
     CURIAM
    -0.60
    InputTagHelper
    -0.60
    OGND
    -0.59
     kasarigan
    -0.58
    ValueGeneration
    -0.57
    migrationBuilder
    -0.57
    modelBuilder
    -0.56
    POSITIVE LOGITS
     last
    3.31
    last
    2.87
    Last
    2.68
     última
    2.62
     Last
    2.62
     terakhir
    2.58
     último
    2.56
     dernière
    2.53
     dernier
    2.51
     LAST
    2.48
    Activations Density 0.330%

    No Known Activations