© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7459
    Prev
    Next
    INDEX
    Explanations

    references to mathematics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1705
    +0.16
    0.6%
    1331
    +0.14
    0.5%
    1387
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.16
    0.03
    1705
    +0.14
    0.03
    1125
    +0.12
    0.02
    Negative Logits
    twimg
    -0.52
    cloudflare
    -0.52
    flashdata
    -0.47
    putExtra
    -0.45
    ExtendWith
    -0.45
    IsContent
    -0.43
     Wide
    -0.43
    getItemId
    -0.42
     Krise
    -0.42
    CrossOrigin
    -0.41
    POSITIVE LOGITS
     math
    1.19
     mathematics
    1.06
    math
    1.01
     MATH
    1.01
     mathematical
    0.98
     maths
    0.97
    Math
    0.96
     Math
    0.96
    Mathematical
    0.94
     Mathematics
    0.91
    Activations Density 0.074%

    No Known Activations