© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2318
    Prev
    Next
    INDEX
    Explanations

    special symbols or syntax elements in programming code

    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
    enumi
    -0.73
    bitField
    -0.56
    getWriter
    -0.52
    ofan
    -0.51
     getRule
    -0.49
     saved
    -0.49
    tonsoft
    -0.48
    ITUTE
    -0.46
    $_['
    -0.46
     bay
    -0.44
    POSITIVE LOGITS
     fapt
    0.57
    adaptiveStyles
    0.54
     AssemblyCompany
    0.54
     ISNI
    0.53
     Templar
    0.51
     Ambiental
    0.51
    webElement
    0.51
     Enix
    0.50
    Nuorodos
    0.50
    nope
    0.49
    Activations Density 0.046%

    No Known Activations