© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5545
    Prev
    Next
    INDEX
    Explanations

    patterns in numerical or coded information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.85
    bootstrapcdn
    -0.83
    ########.
    -0.80
     ویکی‌پدیای
    -0.78
    出版年
    -0.77
     estimés
    -0.72
    jsii
    -0.72
     BIBSYS
    -0.71
    +#+#
    -0.70
    ništvo
    -0.70
    POSITIVE LOGITS
    География
    0.54
    veien
    0.49
    OrNull
    0.47
     елның
    0.46
    월
    0.45
    capsulation
    0.45
     الاطلاع
    0.45
     
    0.44
    belum
    0.43
     Still
    0.42
    Activations Density 0.126%

    No Known Activations