© 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. 2443
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and their historical context

    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
    System
    -1.02
     System
    -0.97
     SYSTEM
    -0.71
    はじめに
    -0.71
     system
    -0.63
     Systems
    -0.62
    SYSTEM
    -0.60
    Syst
    -0.60
    +#+#
    -0.60
     Système
    -0.59
    POSITIVE LOGITS
    exitRule
    0.55
    Havolalar
    0.52
    Manbalar
    0.50
    djangoproject
    0.50
     sich
    0.49
    ў
    0.49
    java
    0.48
     zich
    0.48
    copyFrom
    0.48
    SuccessListener
    0.47
    Activations Density 0.070%

    No Known Activations