© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12251
    Prev
    Next
    INDEX
    Explanations

    the similarity in mathematical expressions and their associated variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.13
    majánló
    -1.02
    GEBURTSDATUM
    -0.97
     pleaſure
    -0.95
    :✨
    -0.94
     Monfieur
    -0.94
     Efq
    -0.94
    <unused79>
    -0.93
     Dieſe
    -0.93
    <unused3>
    -0.93
    POSITIVE LOGITS
    thy
    0.56
    ate
    0.53
    tra
    0.52
    ut
    0.52
     ann
    0.50
     
    0.50
    b
    0.50
     late
    0.49
     early
    0.48
    ly
    0.47
    Activations Density 0.323%

    No Known Activations