© 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. 2339
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions related to managing data structures and memory operations

    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
    kać
    -0.47
     Lud
    -0.47
     mé
    -0.44
    ]+"
    -0.42
    wms
    -0.41
     baños
    -0.41
     ""
    -0.41
     kotlin
    -0.40
    mez
    -0.40
    Spoljašnje
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.85
     mxArray
    0.77
     disponibilités
    0.75
    ImageContext
    0.74
    ",&
    0.74
     myſelf
    0.73
    Amicalement
    0.73
     intptr
    0.73
     NULL
    0.71
    олові
    0.69
    Activations Density 1.018%

    No Known Activations