© 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. 31-GEMMASCOPE-RES-131K
    11. 5217
    Prev
    Next
    INDEX
    Explanations

    references to articles, publications, and works with a focus on their appearance and context within media

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

    published articles and news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.66
     disambiguazione
    -0.64
    protoimpl
    -0.64
    OGND
    -0.63
     Numerade
    -0.60
    aarrggbb
    -0.59
    NameInMap
    -0.57
    ConstraintMaker
    -0.57
     utafitiHapana
    -0.55
     CURIAM
    -0.55
    POSITIVE LOGITS
     newspaper
    1.04
     published
    1.02
     newspapers
    0.95
     publication
    0.88
    published
    0.85
     magazine
    0.84
     publicado
    0.83
    newspaper
    0.81
     Newspaper
    0.81
    Newspaper
    0.80
    Activations Density 0.058%

    No Known Activations