© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 8022
    Prev
    Next
    INDEX
    Explanations

    sequences of assembly language or low-level programming instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enctype
    -0.53
    melidir
    -0.51
     khảo
    -0.48
     mole
    -0.47
    drv
    -0.46
     Surv
    -0.46
    FactoryBean
    -0.46
     squee
    -0.45
    appli
    -0.45
    mişti
    -0.45
    POSITIVE LOGITS
     registers
    0.69
     EconPapers
    0.63
    Register
    0.60
     Register
    0.59
    AnchorStyles
    0.58
     address
    0.58
     surla
    0.57
     Registers
    0.57
     register
    0.57
    ContentAlignment
    0.56
    Activations Density 1.149%

    No Known Activations