© 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. 14-GEMMASCOPE-RES-16K
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    terms related to digital or computational frameworks, particularly involved in decimation and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.77
     mati
    -0.73
     Шта
    -0.72
     glaubt
    -0.69
     Williams
    -0.69
    Gf
    -0.66
    DebuggerNonUser
    -0.66
    formik
    -0.65
    tigt
    -0.64
     continuant
    -0.62
    POSITIVE LOGITS
     DEC
    1.44
    DEC
    1.31
     Decker
    1.30
     decathlon
    1.10
     Dek
    1.07
     Decks
    1.07
    Dek
    1.05
     Dec
    1.03
     Decoder
    1.02
     Dekker
    1.00
    Activations Density 0.173%

    No Known Activations