© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13700
    Prev
    Next
    INDEX
    Explanations

    concepts related to understanding and thought processes

    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
     sirop
    -0.52
    riva
    -0.52
    tagHelper
    -0.51
    żesz
    -0.50
     sinned
    -0.49
     degeneracy
    -0.49
     doInBackground
    -0.48
    bootstrapcdn
    -0.48
    ยว
    -0.48
    Unders
    -0.47
    POSITIVE LOGITS
     understand
    0.65
     understanding
    0.64
     Understand
    0.64
     understands
    0.62
    Understand
    0.61
    Understanding
    0.60
    ніципалі
    0.59
     Taman
    0.59
     Paglinawan
    0.57
     comprender
    0.56
    Activations Density 0.303%

    No Known Activations