© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4810
    Prev
    Next
    INDEX
    Explanations

    metrics related to user behavior and system vulnerabilities

    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
    1.2%
    1842
    +0.15
    0.6%
    468
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.33
    0.04
    1842
    +0.15
    0.04
    332
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.30
    /***
    -0.81
     négociations
    -0.70
     déclarations
    -0.69
     prochaines
    -0.66
     témoignages
    -0.65
     procédures
    -0.63
    /*!
    -0.62
    ⓧ
    -0.61
     échanges
    -0.61
    POSITIVE LOGITS
     riva
    1.06
     magis
    1.05
     sentra
    1.04
     maroc
    1.00
     Minang
    0.99
     lele
    0.99
     nomine
    0.95
     bandung
    0.95
     intest
    0.95
     carc
    0.95
    Activations Density 1.142%

    No Known Activations