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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8169
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic properties and phenomena

    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
     knex
    -0.46
     Routed
    -0.46
     glucos
    -0.45
     gloria
    -0.45
    pug
    -0.43
     glycogen
    -0.42
     Gelen
    -0.42
     Sequ
    -0.42
     Cox
    -0.42
     Binghamton
    -0.42
    POSITIVE LOGITS
     magnetic
    1.78
     Magnetic
    1.62
    magnetic
    1.58
    Magnetic
    1.58
     magnet
    1.54
     magnets
    1.46
     MAGNET
    1.42
     magnetism
    1.41
     magne
    1.38
    magnet
    1.38
    Activations Density 0.700%

    No Known Activations