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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101974
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.66
    الحياه
    -0.56
     financieras
    -0.51
     Normdatei
    -0.50
     dezelve
    -0.49
    ITERATURE
    -0.49
    Datuak
    -0.49
     leſs
    -0.49
     AssemblyCulture
    -0.48
     bisous
    -0.47
    POSITIVE LOGITS
    Xna
    0.45
    uxxxx
    0.40
    تقاوى
    0.37
     ""],
    0.36
     太郎
    0.35
    AddWithValue
    0.35
     blog
    0.35
    twimg
    0.34
     contextLoads
    0.34
    tangentMode
    0.34
    Activations Density 0.026%

    No Known Activations