© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3726
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections within a context

    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
    +0.14
    0.6%
    1892
    +0.12
    0.5%
    538
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.14
    0.05
    1905
    +0.12
    0.04
    1667
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.69
    ⓧ
    -1.14
     endeavored
    -0.86
    <?
    -0.84
     endeavoured
    -0.82
    /**
    -0.78
     strove
    -0.78
    
    -0.76
     renounced
    -0.71
     rejoined
    -0.70
    POSITIVE LOGITS
    !!</
    1.09
     :)</
    1.01
     maroc
    1.00
     manuten
    0.94
     miniatura
    0.93
     dises
    0.93
     applau
    0.92
     ?</
    0.91
     ados
    0.91
     ananas
    0.91
    Activations Density 0.105%

    No Known Activations