© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 13950
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to creation and authorship

    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
    Ljava
    -0.35
    DispatchToProps
    -0.32
    Selection
    -0.32
    Statut
    -0.30
     State
    -0.30
     Selection
    -0.30
    machung
    -0.29
     UP
    -0.28
     Working
    -0.28
    }{*}{
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.78
     ویکی‌پدی
    0.77
     CreateTagHelper
    0.67
    Jeografia
    0.59
     transfieras
    0.59
    ⤹
    0.56
     EconPapers
    0.55
     propOrder
    0.54
     yym
    0.54
    請繼續往下閱讀
    0.54
    Activations Density 0.283%

    No Known Activations