© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2664
    Prev
    Next
    INDEX
    Explanations

    dates, specifically in relation to events or happenings

    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
    +0.20
    1.1%
    506
    +0.11
    0.6%
    1387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.20
    0.04
    1387
    +0.11
    0.04
    332
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.93
    ⓧ
    -0.92
    GTCX
    -0.89
    EndProject
    -0.79
    addComponent
    -0.77
    RouterModule
    -0.77
    ConverterFactory
    -0.71
    /*++
    -0.70
     GenerationType
    -0.70
    ///
    -0.70
    POSITIVE LOGITS
     impra
    1.96
     maneu
    1.94
     affor
    1.93
     increa
    1.86
     reluct
    1.77
     indestru
    1.76
     Juf
    1.75
     intermitt
    1.75
     accla
    1.73
     Simult
    1.73
    Activations Density 0.040%

    No Known Activations