© 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. 257
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis methods and procedures

    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
    876
    +0.20
    0.8%
    50
    +0.15
    0.6%
    283
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.20
    -0.01
    1499
    +0.15
    0.09
    283
    +0.15
    0.02
    Negative Logits
    <bos>
    -2.59
    HasForeignKey
    -0.92
     AssemblyCompany
    -0.88
    HasColumnType
    -0.83
    ⓧ
    -0.83
     at
    -0.81
    TargetException
    -0.80
    Além
    -0.79
     sold
    -0.78
    SuccessListener
    -0.77
    POSITIVE LOGITS
     effe
    2.91
     aen
    2.82
     increa
    2.73
     emphat
    2.69
     ftu
    2.66
     thut
    2.64
     maneu
    2.61
     nece
    2.56
     inev
    2.56
     ?...
    2.55
    Activations Density 0.691%

    No Known Activations