© 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. 4020
    Prev
    Next
    INDEX
    Explanations

    terms indicating effectiveness or efficiency

    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
    +0.26
    1.5%
    874
    +0.14
    0.8%
    650
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.26
    0.03
    47
    +0.14
    0.02
    1233
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.86
    /***
    -0.74
    //---
    -0.71
     peered
    -0.63
     ratify
    -0.63
     enshr
    -0.63
     forbade
    -0.63
     strolled
    -0.62
     strode
    -0.62
     leaped
    -0.61
    POSITIVE LOGITS
     saar
    1.30
     jaya
    1.19
     riva
    1.12
     liev
    1.08
     bandung
    1.04
     kasa
    1.03
     territo
    1.03
     parati
    1.01
     sentra
    1.01
     alha
    1.01
    Activations Density 0.038%

    No Known Activations