© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12704
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to linear algebra concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron is looking for mathematical notation containing "\mathbb" commands that represent special number sets in mathematical formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pleaſure
    -0.66
    ſelves
    -0.65
     ſtate
    -0.63
     Houſe
    -0.60
    newVal
    -0.58
     themſelves
    -0.57
     ſy
    -0.57
     houſe
    -0.57
     ſtand
    -0.56
     Conſ
    -0.55
    POSITIVE LOGITS
     Mechanism
    0.60
    aria
    0.60
    riae
    0.60
     Willis
    0.59
    isio
    0.58
     Mechanisms
    0.58
     mechanisms
    0.57
    axis
    0.57
    Locus
    0.57
    titia
    0.57
    Activations Density 0.351%

    No Known Activations