© 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. 21-GEMMASCOPE-RES-16K
    11. 8957
    Prev
    Next
    INDEX
    Explanations

    elements related to academic achievements and professional titles

    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
    ReusableCell
    -0.90
    NameInMap
    -0.88
     nahilalakip
    -0.84
    GEBURTSDATUM
    -0.83
    
    -0.79
     kaynağından
    -0.79
     дописавши
    -0.78
    +#+#
    -0.75
     ſche
    -0.75
     ModelExpression
    -0.73
    POSITIVE LOGITS
     at
    2.71
     tại
    1.88
     presso
    1.84
     chez
    1.38
     	e
    1.25
    at
    1.24
    At
    1.15
     At
    1.12
     בבית
    1.11
     ở
    1.09
    Activations Density 1.004%

    No Known Activations