© 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. 2218
    Prev
    Next
    INDEX
    Explanations

    references to companies and their corporate structure

    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
    +0.28
    1.3%
    2015
    +0.14
    0.6%
    783
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.28
    0.01
    683
    +0.14
    0.10
    270
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.58
     prioritise
    -0.87
     
    -0.79
     stopp
    -0.74
     proactively
    -0.70
     byt
    -0.69
     incentiv
    -0.65
     dut
    -0.64
     prioritize
    -0.64
     ensure
    -0.64
    POSITIVE LOGITS
     Traité
    1.13
     javier
    1.08
     Mejía
    1.05
     felipe
    1.05
     [''
    1.05
     eduardo
    1.04
     vœ
    1.04
     Spéc
    1.04
     fameux
    1.03
     jugement
    1.01
    Activations Density 6.170%

    No Known Activations