© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5115
    Prev
    Next
    INDEX
    Explanations

    references to CPU and processor performance

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    1.3%
    370
    +0.12
    0.7%
    1806
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.23
    0.02
    31
    +0.12
    0.01
    1142
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.92
     intersper
    -1.39
     shenan
    -0.98
     underval
    -0.95
     harmonize
    -0.94
     amass
    -0.92
     rouse
    -0.91
     racon
    -0.90
     endeavored
    -0.90
     banish
    -0.88
    POSITIVE LOGITS
    CPU
    1.15
     CPU
    1.14
    cpu
    1.08
     cpu
    0.99
    Cpu
    0.98
     jawa
    0.91
     CPUs
    0.89
     frambo
    0.87
     Février
    0.83
     ananas
    0.81
    Activations Density 0.030%

    No Known Activations