© 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. 7-GEMMASCOPE-RES-16K
    11. 13806
    Prev
    Next
    INDEX
    Explanations

    mentions of universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.55
    fromLTRB
    -0.50
    chatron
    -0.45
    ggior
    -0.45
    Halo
    -0.43
    хьтан
    -0.43
    coarse
    -0.43
    stick
    -0.43
     poign
    -0.43
    himovic
    -0.42
    POSITIVE LOGITS
     University
    2.45
    University
    2.25
     university
    2.25
     UNIVERSITY
    2.08
    university
    1.98
     universities
    1.65
     Universities
    1.63
     Univ
    1.59
     universidad
    1.54
    UNIVERSITY
    1.51
    Activations Density 0.060%

    No Known Activations