© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8513
    Prev
    Next
    INDEX
    Explanations

    technical and medical terminology related to various fields, including algorithmic functions, biological conditions, and sensory or cognitive states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.32
     will
    -0.29
     is
    -0.28
    full
    -0.28
     while
    -0.28
     once
    -0.28
     none
    -0.28
     
    -0.27
     new
    -0.27
     so
    -0.26
    POSITIVE LOGITS
    quelize
    0.97
    OGND
    0.87
    verwijspagina
    0.83
    Diweddarwch
    0.83
     betweenstory
    0.82
    plotlib
    0.80
    ſelves
    0.79
    chestra
    0.79
    uxxxx
    0.79
    tonsoft
    0.78
    Activations Density 1.575%

    No Known Activations