© 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. 10-GEMMASCOPE-RES-16K
    11. 3441
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and possibly locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.80
    الحياه
    -0.71
     autorytatywna
    -0.70
     CanadaChoose
    -0.69
     vulgaires
    -0.65
    GEBURTSDATUM
    -0.65
     препратки
    -0.63
     distanciation
    -0.62
    úgó
    -0.62
    kuuta
    -0.61
    POSITIVE LOGITS
    <bos>
    0.65
    BatchNorm
    0.58
     McC
    0.55
     actionMode
    0.54
     Ko
    0.53
     cellpadding
    0.53
     MonoBehaviour
    0.50
    McC
    0.50
     Mer
    0.50
     Mc
    0.49
    Activations Density 0.312%

    No Known Activations