© 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. 10089
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate summary sections or references to remaining content within a document

    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
    
    -1.15
     المعرف
    -1.05
    OGND
    -1.01
    tvguidetime
    -1.00
    HasAnnotation
    -0.94
    crapers
    -0.93
    حوالہ
    -0.93
    ellees
    -0.92
     MessageBoxIcon
    -0.92
     Marlowe
    -0.92
    POSITIVE LOGITS
     rest
    1.54
    Rest
    1.47
     Rest
    1.46
     REST
    1.38
    rest
    1.37
    REST
    1.27
    most
    1.07
     resten
    0.93
     rests
    0.90
     resting
    0.87
    Activations Density 0.048%

    No Known Activations