© 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. 22-GEMMASCOPE-RES-16K
    11. 15040
    Prev
    Next
    INDEX
    Explanations

    terminals related to advanced scientific technologies and methodologies

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

    Followed by "on", "as", "to", or "-"

    np_acts-logits-general · gemini-2.0-flash

    words followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.61
    \\
    -0.60
     ,
    -0.60
    altezza
    -0.58
       
    -0.55
    tų
    -0.54
    ↵↵↵↵
    -0.53
     imidlertid
    -0.53
     supérieures
    -0.52
     .
    -0.51
    POSITIVE LOGITS
    RegressionTest
    0.86
    évaluateur
    0.80
    )");
    0.76
     typelib
    0.74
     TextAppearance
    0.72
    CloseOperation
    0.71
     -->>
    0.70
     inad
    0.68
    aarrggbb
    0.68
     himo
    0.68
    Activations Density 0.039%

    No Known Activations