© 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. 36-GEMMASCOPE-RES-16K
    11. 5420
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and other related articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.52
    Textbook
    -0.51
    newtheorem
    -0.51
     defaultstate
    -0.50
     ${({
    -0.50
     groupBox
    -0.49
     myſelf
    -0.48
    Vidite
    -0.48
    styleUrls
    -0.47
    RequestQueue
    -0.47
    POSITIVE LOGITS
     resulting
    0.76
     gesture
    0.70
     kyse
    0.66
     feat
    0.64
     move
    0.63
     endeavor
    0.62
     συγ
    0.62
     effort
    0.59
     démarche
    0.59
     hacerlo
    0.58
    Activations Density 0.827%

    No Known Activations