© 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. 16269
    Prev
    Next
    INDEX
    Explanations

    terms associated with significant or notable events or entities labeled as "grand."

    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
     ?>>
    -0.77
    DBObject
    -0.77
    脚注の使い方
    -0.76
     KTP
    -0.72
    bake
    -0.71
    ymce
    -0.69
     Shee
    -0.69
    solicit
    -0.67
     $$
    -0.66
    AutoField
    -0.66
    POSITIVE LOGITS
    rinfo
    0.85
    rawdę
    0.78
    alised
    0.78
    wwwwwwww
    0.76
     ViewController
    0.76
     Chord
    0.75
     pudesse
    0.75
     possam
    0.74
     Dray
    0.73
     GRAND
    0.73
    Activations Density 0.120%

    No Known Activations