© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    references to specific appliance parts and their associated functions

    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
     archery
    -0.62
     متحده
    -0.61
     مشين
    -0.60
     habet
    -0.59
     paintball
    -0.58
    ⋙
    -0.58
     ?>/
    -0.58
     airfield
    -0.57
     Archery
    -0.57
    tagHelperRunner
    -0.57
    POSITIVE LOGITS
     settings
    0.75
     Settings
    0.68
     programma
    0.60
     SETTINGS
    0.60
     preset
    0.59
     setting
    0.57
     timer
    0.55
     operator
    0.54
     mode
    0.53
     programmation
    0.53
    Activations Density 0.164%

    No Known Activations