© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 16818
    Prev
    Next
    INDEX
    Explanations

    mentions of keywords related to technical or academic subjects

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

    Keywords:

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     protoimpl
    -0.45
    webElementXpaths
    -0.39
     Lao
    -0.39
    reactstrap
    -0.39
    gebob
    -0.38
    slick
    -0.38
     Tyler
    -0.38
     Biôgrafia
    -0.37
    PU
    -0.37
     Fle
    -0.37
    POSITIVE LOGITS
    Keywords
    3.48
     Keywords
    2.75
     keywords
    2.20
    keywords
    2.20
    KEYWORDS
    2.09
    Keyword
    1.88
     Keyword
    1.81
     keyword
    1.73
    关键词
    1.66
    keyword
    1.62
    Activations Density 0.002%

    No Known Activations