© 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. 35-GEMMASCOPE-RES-16K
    11. 14757
    Prev
    Next
    INDEX
    Explanations

    instances of the word "probation" and variations related to legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.36
     Initializes
    -0.31
     FetchType
    -0.31
     mystery
    -0.30
     SLP
    -0.30
    beck
    -0.29
    ыгана
    -0.28
     LIABLE
    -0.26
    TPS
    -0.26
     quæ
    -0.26
    POSITIVE LOGITS
     disambiguazione
    0.63
    лтемелер
    0.61
    Tembelea
    0.57
    balleur
    0.57
    rungsseite
    0.57
     EconPapers
    0.55
    UserScript
    0.55
    InstanceState
    0.52
     незавершена
    0.51
    msgSender
    0.51
    Activations Density 0.184%

    No Known Activations