© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 230
    Prev
    Next
    INDEX
    Explanations

    phrases related to borrowing money at low interest rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.31
    1.3%
    876
    +0.12
    0.5%
    1385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.31
    0.07
    32
    +0.12
    0.07
    1482
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.48
    Referències
    -0.61
     jsPsych
    -0.58
     put
    -0.56
    IActionResult
    -0.56
     swore
    -0.54
    لينكات
    -0.54
    Threading
    -0.53
     Congress
    -0.53
     Europe
    -0.53
    POSITIVE LOGITS
     swarovski
    1.59
     tupperware
    1.42
     sappi
    1.41
     hairc
    1.31
     eiffel
    1.29
     maroc
    1.24
     matel
    1.24
     ibiza
    1.22
     michelin
    1.20
     lamborghini
    1.19
    Activations Density 0.230%

    No Known Activations