© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2694
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in text

    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
    1343
    +0.14
    0.7%
    478
    +0.12
    0.6%
    1222
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.02
    478
    +0.12
    0.01
    1124
    +0.09
    0.01
    Negative Logits
    <bos>
    -2.42
    ⓧ
    -1.09
    <?
    -1.07
    /***
    -1.02
    
    -0.98
    /**
    -0.89
    <?
    -0.80
    ItemBackground
    -0.72
     disbur
    -0.71
    /*
    -0.70
    POSITIVE LOGITS
     particolar
    1.12
     éto
    0.90
     bicic
    0.90
     maroc
    0.89
     waer
    0.87
     mû
    0.87
     wien
    0.87
     dises
    0.87
     onore
    0.86
    emmel
    0.86
    Activations Density 0.018%

    No Known Activations