© 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. 9-GEMMASCOPE-RES-16K
    11. 10031
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and methodology related to research studies

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

    section headings and transition statements in scientific or academic papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    ChildScrollView
    -0.44
     financiación
    -0.39
     mourir
    -0.38
     reputación
    -0.38
     Tatsache
    -0.37
     sija
    -0.37
    aarrggbb
    -0.36
    TargetException
    -0.35
    httphttps
    -0.35
     enjoyment
    -0.35
    POSITIVE LOGITS
    msgTypes
    0.59
    arXiv
    0.59
    BeginContext
    0.56
     Normdatei
    0.54
    __':
    0.50
    archiviato
    0.50
     CURIAM
    0.47
     surla
    0.47
     informée
    0.47
    mybatisplus
    0.46
    Activations Density 3.126%

    No Known Activations