© 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. 3-GEMMASCOPE-RES-16K
    11. 8816
    Prev
    Next
    INDEX
    Explanations

    references to specific editions of publications

    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
    atisk
    -0.58
     Graves
    -0.57
    RRRR
    -0.56
    Graves
    -0.55
    *}$
    -0.54
    treeNode
    -0.54
    centages
    -0.53
    PositiveButton
    -0.52
    mose
    -0.52
    curacies
    -0.51
    POSITIVE LOGITS
     Edition
    3.25
     edition
    3.22
    Edition
    2.95
    edition
    2.91
     EDITION
    2.85
     editions
    2.75
     Editions
    2.20
     édition
    2.13
     edición
    1.91
     edição
    1.74
    Activations Density 0.059%

    No Known Activations