Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    expressions of intention and purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.97
     חיצוניים
    -0.93
     GoogleFonts
    -0.88
     nakalista
    -0.85
     NSCoder
    -0.83
    ModelSerializer
    -0.81
     Audiodateien
    -0.78
     незавершена
    -0.77
    NameInMap
    -0.75
    Discography
    -0.74
    POSITIVE LOGITS
     intended
    1.32
    intent
    1.32
     intent
    1.31
     intends
    1.30
     intend
    1.25
     Intent
    1.24
    Intent
    1.22
     Inten
    1.22
     Intended
    1.22
     intending
    1.21
    Activations Density 0.105%

    No Known Activations