© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7662
    Prev
    Next
    INDEX
    Explanations

    words indicating size or scale, particularly "smaller"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enlarge
    -0.63
     enlargement
    -0.56
     enlar
    -0.56
     enlarged
    -0.52
     Enlarge
    -0.52
    ']>
    -0.50
    WithIOException
    -0.49
     Мексичка
    -0.48
    AutoField
    -0.47
    awtextra
    -0.47
    POSITIVE LOGITS
     smaller
    2.17
     Smaller
    2.06
    Smaller
    2.03
    smaller
    2.00
     shorter
    1.80
     lesser
    1.64
     weaker
    1.54
     lighter
    1.48
     thinner
    1.41
     Shorter
    1.41
    Activations Density 0.137%

    No Known Activations