© 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. 25-GEMMASCOPE-RES-16K
    11. 2273
    Prev
    Next
    INDEX
    Explanations

    complex relationships and interdependencies within scientific or analytical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     They
    -0.78
    them
    -0.69
     THEM
    -0.69
     kasarigan
    -0.68
    ेशा
    -0.63
    TagMode
    -0.62
    imageshack
    -0.59
    SqlSession
    -0.58
     Мой
    -0.58
    complexContent
    -0.58
    POSITIVE LOGITS
     we
    3.93
     мы
    2.00
    we
    1.80
    我們
    1.77
    我们
    1.75
    We
    1.61
     nous
    1.43
     ourselves
    1.42
     abbiamo
    1.40
    私たちは
    1.38
    Activations Density 1.469%

    No Known Activations