© 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. 358
    Prev
    Next
    INDEX
    Explanations

    references to official documents or processes related to public records and allegations

    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
    +0.35
    1.8%
    1150
    +0.18
    0.9%
    1577
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.35
    0.20
    1150
    +0.18
    0.09
    946
    +0.15
    0.18
    Negative Logits
    <bos>
    -2.71
     nutella
    -1.35
     intersper
    -1.28
     swarovski
    -1.14
     oreo
    -1.13
     ecru
    -1.11
     forbear
    -1.11
     bonbons
    -1.09
     amigurumi
    -1.06
     hairc
    -1.00
    POSITIVE LOGITS
     Pekan
    0.85
     Muhamma
    0.83
     Medan
    0.80
     Tanjung
    0.74
     Teknik
    0.74
     Palembang
    0.72
     Lübeck
    0.71
     Bekasi
    0.69
     Pasir
    0.69
     DKI
    0.68
    Activations Density 12.645%

    No Known Activations