© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 1459
    Prev
    Next
    INDEX
    Explanations

    specific names of individuals and companies, especially those associated with film and production, as well as geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.89
    LLocation
    -0.84
     Audiodateien
    -0.84
     PPM
    -0.83
     TestBed
    -0.82
     Jol
    -0.80
    PreferredItem
    -0.78
    SceneManagement
    -0.78
    nass
    -0.76
    躇
    -0.74
    POSITIVE LOGITS
    بوابة
    0.95
     Riz
    0.79
     Hooker
    0.78
    لينا
    0.76
     Babcock
    0.74
     '\\;'
    0.71
     alre
    0.69
     Telecom
    0.67
     Hendricks
    0.67
     courtier
    0.66
    Activations Density 2.139%

    No Known Activations