© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4450
    Prev
    Next
    INDEX
    Explanations

    terms related to decreases and reductions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.57
    resaid
    -0.54
    quatch
    -0.52
     okuyayım
    -0.51
     StringTokenizer
    -0.51
    ernalia
    -0.50
    ++++++++++++++++
    -0.49
     încă
    -0.49
    osoba
    -0.48
    NameInMap
    -0.48
    POSITIVE LOGITS
     decrease
    1.01
     down
    0.99
     lowering
    0.97
    down
    0.90
     decreased
    0.90
     lowered
    0.88
     decreasing
    0.86
     Decrease
    0.85
    decrease
    0.84
     пони
    0.84
    Activations Density 1.521%

    No Known Activations