© 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. 2-GEMMASCOPE-RES-16K
    11. 15615
    Prev
    Next
    INDEX
    Explanations

    references to memory addresses or pointers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.86
    awtextra
    -0.71
    IsContent
    -0.63
     समीक्षाओं
    -0.63
     Италијани
    -0.62
     disambiguazione
    -0.60
     nahilalakip
    -0.60
     चीज़ों
    -0.60
    ⎠
    -0.58
    ьажоргаш
    -0.57
    POSITIVE LOGITS
    vice
    0.59
     *++
    0.58
     Manajemen
    0.57
    getahuan
    0.56
    drav
    0.52
     Mammoth
    0.50
    CurrentValue
    0.50
     Movers
    0.50
    bindParam
    0.49
     emergent
    0.49
    Activations Density 0.717%

    No Known Activations