© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 3089
    Prev
    Next
    INDEX
    Explanations

    data related to financial systems and processes

    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
    '])->
    -0.55
    ")));
    
    -0.52
    SourceChecksum
    -0.52
     security
    -0.49
    ']=$
    -0.49
     }}</
    -0.48
    '},
    
    -0.45
    MigrationBuilder
    -0.45
     riten
    -0.43
    +)$
    -0.43
    POSITIVE LOGITS
     plots
    0.68
     Matlab
    0.68
     plotting
    0.66
    存于互联网档案馆
    0.65
     dataset
    0.65
     filenames
    0.63
     jsPsych
    0.63
     experimento
    0.62
     datasets
    0.61
    matlab
    0.61
    Activations Density 1.002%

    No Known Activations