© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2010
    Prev
    Next
    INDEX
    Explanations

    topics related to legal investigations and inquiries

    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
    1842
    +0.25
    1.0%
    50
    +0.23
    0.9%
    344
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.25
    0.09
    946
    +0.23
    0.05
    1776
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.80
     encomp
    -1.19
     intersper
    -1.19
     swarovski
    -1.15
     hairc
    -1.12
     nutella
    -1.10
     tupperware
    -1.05
     ecru
    -0.98
    ⓧ
    -0.97
     oreo
    -0.93
    POSITIVE LOGITS
     teras
    1.00
     Palembang
    0.94
     lele
    0.89
     saar
    0.87
     uhr
    0.86
     kuli
    0.84
     Demok
    0.84
     kac
    0.83
     kado
    0.83
     kasa
    0.83
    Activations Density 1.162%

    No Known Activations