© 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. 3-GEMMASCOPE-RES-16K
    11. 10387
    Prev
    Next
    INDEX
    Explanations

    references to cells and cell-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.80
     doInBackground
    -0.77
    hoga
    -0.72
    TintMode
    -0.71
     setuptools
    -0.71
     SPIE
    -0.68
     valmis
    -0.68
     Journ
    -0.68
     AssemblyTitle
    -0.68
     wishlist
    -0.66
    POSITIVE LOGITS
     cell
    3.35
    cell
    3.28
     Cell
    3.22
    Cell
    3.13
     CELL
    3.11
    CELL
    2.93
     cells
    2.66
    cells
    2.55
     Cells
    2.54
    Cells
    2.46
    Activations Density 0.128%

    No Known Activations