© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7503
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names or mentions of schools

    np_acts-logits-general · gemini-2.0-flash

    grammar school education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.60
    TagMode
    -0.59
     Reſ
    -0.53
    ſelves
    -0.52
     leſs
    -0.51
    󰀄
    -0.51
     виправивши
    -0.51
     ſtate
    -0.50
     ujednoznacz
    -0.50
     purpoſe
    -0.50
    POSITIVE LOGITS
     keb
    0.39
     aprendiz
    0.37
    CrossRef
    0.34
     artic
    0.31
     starters
    0.31
     pok
    0.31
     h
    0.31
     aliqu
    0.30
     manipulations
    0.30
     appointments
    0.30
    Activations Density 0.121%

    No Known Activations