© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16435
    Prev
    Next
    INDEX
    Explanations

    special tokens that signify the beginning of a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     greateſt
    -0.96
     myſelf
    -0.96
     auffi
    -0.96
     Theſe
    -0.96
     utafitiHapana
    -0.94
     ſeveral
    -0.94
     purpoſe
    -0.93
     Anſ
    -0.91
     themſelves
    -0.91
     entanto
    -0.90
    POSITIVE LOGITS
     e
    0.55
     indeed
    0.50
     και
    0.50
    glory
    0.50
     
    0.50
    amp
    0.50
    BackStack
    0.49
     op
    0.49
     o
    0.48
    datac
    0.47
    Activations Density 0.010%

    No Known Activations