© 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. 3-GEMMASCOPE-RES-16K
    11. 10727
    Prev
    Next
    INDEX
    Explanations

    measurements of physical dimensions or area

    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
     BorderSide
    -0.44
    embolso
    -0.43
     puentes
    -0.42
     Arabia
    -0.41
     Schiffe
    -0.40
     Vorbild
    -0.38
     Dichtung
    -0.38
     penghar
    -0.38
     dibujos
    -0.37
     ARAB
    -0.36
    POSITIVE LOGITS
     تضيفلها
    0.59
    MLLoader
    0.56
    Jeografia
    0.55
    ➯
    0.51
     للمعارف
    0.50
    mobileqq
    0.50
    pogon
    0.49
    WithMany
    0.49
    ⓧ
    0.49
    InputTagHelper
    0.48
    Activations Density 0.045%

    No Known Activations