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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8581
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the"

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

    Immediately precedes "License"

    np_acts-logits-general · gemini-2.0-flash

    license and compliance

    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
    
    -0.75
     solchen
    -0.74
     propOrder
    -0.66
    own
    -0.65
     ciascuno
    -0.64
     solche
    -0.63
     automatiques
    -0.61
    both
    -0.61
     zoude
    -0.61
    seamnă
    -0.61
    POSITIVE LOGITS
     same
    1.51
     following
    1.22
     latter
    1.22
     entire
    1.21
     rest
    1.12
    ophyll
    1.09
     most
    1.04
     whole
    1.04
    matically
    1.03
     aforementioned
    0.95
    Activations Density 0.130%

    No Known Activations