© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-GEMMASCOPE-RES-16K
    11. 16366
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight benefits or advantages of a system or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podjela
    -0.61
     beginnetje
    -0.58
     Italijanski
    -0.56
     calculées
    -0.54
    InitVars
    -0.54
    หมือน
    -0.54
    DockStyle
    -0.53
    parsedMessage
    -0.52
    DataMember
    -0.50
     متعلقه
    -0.49
    POSITIVE LOGITS
     performance
    1.35
     efficiency
    1.29
     accuracy
    1.26
     reliability
    1.25
     effectiveness
    1.08
     quality
    1.04
     flexibility
    1.03
     productivity
    1.01
    performance
    1.00
     efficacy
    0.99
    Activations Density 0.916%

    No Known Activations