© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13259
    Prev
    Next
    INDEX
    Explanations

    references to specific researchers and their works in academic contexts

    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
     Bex
    -0.81
     XF
    -0.80
     GX
    -0.80
     Sexton
    -0.76
    mX
    -0.75
     Xer
    -0.73
     Ox
    -0.72
     Texan
    -0.71
    uberge
    -0.71
    Ox
    -0.69
    POSITIVE LOGITS
     Schur
    0.94
     وتسجيلات
    0.86
    Swar
    0.85
     knots
    0.85
     Pisa
    0.84
     Etrus
    0.82
     Knot
    0.80
     knot
    0.78
     nakalista
    0.78
     Swar
    0.77
    Activations Density 1.125%

    No Known Activations