© 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. 28-GEMMASCOPE-RES-16K
    11. 7399
    Prev
    Next
    INDEX
    Explanations

    instances of reported events or claims related to significant actions

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

    "For the first time" or similar initial mentions

    np_acts-logits-general · gemini-2.0-flash

    for the first time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     старости
    -0.42
    InjectAttribute
    -0.41
    bcryptjs
    -0.37
    rachtet
    -0.35
    Rinse
    -0.34
    󠁿
    -0.34
    裔
    -0.33
    uksessa
    -0.33
     Bun
    -0.33
    nelle
    -0.32
    POSITIVE LOGITS
     впервые
    1.89
     erstmals
    1.72
    初めて
    1.65
     first
    1.50
    首次
    1.48
    第一次
    1.45
     впер
    1.34
     popr
    1.34
    初めての
    1.22
     pertama
    1.20
    Activations Density 0.503%

    No Known Activations