© 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. 2460
    Prev
    Next
    INDEX
    Explanations

    references to mathematical expressions and notations

    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
    +0.19
    0.8%
    871
    +0.10
    0.4%
    281
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.19
    0.10
    227
    +0.10
    0.10
    304
    +0.09
    -0.02
    Negative Logits
    <bos>
    -2.65
    ⓧ
    -0.84
    /*!
    -0.75
    <?
    -0.72
    /***
    -0.69
    
    -0.64
    rungsseite
    -0.62
     Italijani
    -0.59
    andaag
    -0.59
    HasIndex
    -0.57
    POSITIVE LOGITS
     affor
    1.16
     maneu
    1.13
     stockholm
    1.12
     accla
    1.02
     fortn
    1.00
     increa
    0.99
     sandra
    0.99
     inev
    0.97
     impra
    0.97
     wherea
    0.96
    Activations Density 0.985%

    No Known Activations