© 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. 3938
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and."

    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
    +0.33
    1.7%
    2019
    +0.17
    0.9%
    492
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1507
    +0.33
    0.10
    1892
    +0.17
    0.09
    30
    +0.09
    0.09
    Negative Logits
    <bos>
    -2.83
    ⓧ
    -0.75
    
    -0.75
    <?
    -0.71
    expandindo
    -0.70
    <?
    -0.67
    /***
    -0.67
     دیکھیے
    -0.67
    RTEE
    -0.64
     referenties
    -0.59
    POSITIVE LOGITS
     maneu
    1.05
     disgra
    0.89
     shenan
    0.83
     accla
    0.82
     disagre
    0.77
     reluct
    0.77
     beverly
    0.76
     épu
    0.76
     affor
    0.75
     invin
    0.75
    Activations Density 0.433%

    No Known Activations