© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    references to specific researchers and their collaborations

    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
    453
    +0.21
    0.9%
    1741
    +0.15
    0.7%
    50
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.21
    0.09
    227
    +0.15
    0.07
    613
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.25
    ⓧ
    -0.61
    
    -0.56
     defray
    -0.54
    <?
    -0.50
    /**
    -0.50
    .
    -0.48
    ,
    -0.48
     بتاريخ
    -0.48
    ///////////////
    -0.47
    POSITIVE LOGITS
     viciss
    0.72
     sappi
    0.69
     maksi
    0.65
     vété
    0.64
     keramik
    0.64
     vivement
    0.64
     kosme
    0.64
     applau
    0.63
     karton
    0.63
     parec
    0.63
    Activations Density 0.805%

    No Known Activations