© 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. 19-GEMMASCOPE-RES-16K
    11. 6040
    Prev
    Next
    INDEX
    Explanations

    instances of confusion or complication in processes and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нибудь
    -0.52
     daarom
    -0.50
    chige
    -0.50
     sababu
    -0.49
     nationaux
    -0.49
    صابة
    -0.48
     fordi
    -0.48
    久了
    -0.48
    انون
    -0.46
     deshalb
    -0.45
    POSITIVE LOGITS
     apparently
    2.93
    apparently
    2.81
     Apparently
    2.76
     evidently
    2.67
    Apparently
    2.66
     seems
    2.53
     seem
    2.42
     Evidently
    2.38
    seems
    2.37
     Seems
    2.34
    Activations Density 0.996%

    No Known Activations