© 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. 20-GEMMASCOPE-RES-16K
    11. 421
    Prev
    Next
    INDEX
    Explanations

    characters possessing unique superhuman abilities and transformations

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

    Ability to perform actions

    np_acts-logits-general · gemini-2.0-flash

    abilities or powers to act

    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
     <>",
    -0.66
    Crumb
    -0.65
    Sucesor
    -0.65
     chrétienne
    -0.63
    føl
    -0.57
     Bayes
    -0.57
    reamble
    -0.56
     polaire
    -0.55
     stratigraphy
    -0.55
     econó
    -0.55
    POSITIVE LOGITS
     powers
    1.09
     magic
    1.03
     magical
    1.02
    powers
    0.92
     power
    0.84
    magical
    0.81
     magically
    0.80
     abilities
    0.78
    magic
    0.78
     ability
    0.78
    Activations Density 0.563%

    No Known Activations