© 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. 30-GEMMASCOPE-RES-16K
    11. 14810
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mathematics and mathematical research

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

    Mathematics, often abbreviated

    np_acts-logits-general · gemini-2.0-flash

    mathematical journals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.37
    synthesize
    -0.35
    InitStruct
    -0.33
    <?
    -0.31
    addGap
    -0.31
     pyram
    -0.29
     BrowserModule
    -0.29
    tanie
    -0.27
    Manifest
    -0.27
    propto
    -0.27
    POSITIVE LOGITS
     mathematicians
    1.09
     mathematics
    1.03
     mathematical
    1.00
     Mathematical
    0.95
     mathematician
    0.92
     Mathematics
    0.89
    mathematics
    0.85
    数学
    0.84
     math
    0.83
    Mathematical
    0.82
    Activations Density 1.606%

    No Known Activations