© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14513
    Prev
    Next
    INDEX
    Explanations

    references to parts and sections within a document or report

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تكبرها
    -0.65
    audiovisuel
    -0.61
    hoes
    -0.61
    initializeApp
    -0.59
     autorità
    -0.59
    🏻‍♀️
    -0.58
     próprios
    -0.56
    apimachinery
    -0.55
     $_[
    -0.55
    imply
    -0.54
    POSITIVE LOGITS
    Parts
    0.94
     Parts
    0.88
     parts
    0.85
     PARTS
    0.82
    cip
    0.80
    parts
    0.79
    ridge
    0.71
    ThroughAttribute
    0.69
     PART
    0.67
    PARTS
    0.66
    Activations Density 0.100%

    No Known Activations