© 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. 35-GEMMASCOPE-RES-16K
    11. 10181
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to advanced theories and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.39
    ystis
    -0.37
    ématiques
    -0.36
     ①
    -0.35
     Eti
    -0.35
     Pocket
    -0.35
     acorde
    -0.34
    jsxFileName
    -0.34
    findpost
    -0.33
     Deliber
    -0.33
    POSITIVE LOGITS
     existence
    0.85
     explicit
    0.75
    esistenza
    0.72
    existence
    0.71
     Existence
    0.70
    explicit
    0.69
     theorems
    0.68
    Existence
    0.68
     generalizations
    0.68
     proofs
    0.67
    Activations Density 3.533%

    No Known Activations