© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12964
    Prev
    Next
    INDEX
    Explanations

    phrases related to superconductivity and its underpinning 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
    rungsseite
    -0.65
    تقاوى
    -0.61
     âgées
    -0.59
    ⓧ
    -0.58
    ProgressHUD
    -0.57
     télévisée
    -0.57
     recevrez
    -0.56
    auteuil
    -0.55
     насеље
    -0.54
     équip
    -0.53
    POSITIVE LOGITS
     Slave
    0.60
    Slave
    0.58
     superconducting
    0.57
     insulator
    0.55
     insulating
    0.53
     cup
    0.53
     stripe
    0.53
     Mott
    0.52
     Cooper
    0.52
     Hubbard
    0.52
    Activations Density 1.446%

    No Known Activations