© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 595
    Prev
    Next
    INDEX
    Explanations

    the letter 'l'

    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
    +0.20
    1.2%
    1961
    +0.14
    0.9%
    1265
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1961
    +0.20
    0.02
    1343
    +0.14
    0.02
    1265
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.02
     Queste
    -0.74
     Infatti
    -0.66
    ⓧ
    -0.63
    /*++
    -0.62
    
    -0.62
     Abbiamo
    -0.60
     Puoi
    -0.60
    /**
    -0.59
    /***
    -0.58
    POSITIVE LOGITS
     l
    1.12
     citoy
    0.85
     libéral
    0.84
    l
    0.84
     asiatique
    0.78
     eccl
    0.78
     vulga
    0.73
     japonaise
    0.73
     télévis
    0.72
     incess
    0.72
    Activations Density 0.070%

    No Known Activations