© 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. 6-GEMMASCOPE-RES-16K
    6. 7648
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific and mathematical principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical and scientific terminology related to computer networking, data transmission, and biological systems.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.54
    UVWXYZ
    -0.51
     oč
    -0.49
     mixed
    -0.49
     mid
    -0.48
    baric
    -0.48
    ***********/
    -0.48
     odw
    -0.47
    uarine
    -0.47
    ,{
    -0.46
    POSITIVE LOGITS
    Rohy
    0.70
     mergeFrom
    0.67
    出版年
    0.65
    intenant
    0.63
    SharedDtor
    0.63
     prépar
    0.60
    Geplaatst
    0.60
    centralwidget
    0.59
    millimeters
    0.58
    uktur
    0.57
    Activations Density 0.731%

    No Known Activations