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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1953
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structure in sentence construction

    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
    +0.29
    1.5%
    382
    +0.14
    0.7%
    2019
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.29
    0.16
    2019
    +0.14
    0.14
    2034
    +0.14
    0.14
    Negative Logits
    <bos>
    -3.08
    ⓧ
    -0.81
    
    
    -0.80
    <?
    -0.78
    //*/
    -0.77
     springfox
    -0.76
    amaño
    -0.74
    //});
    -0.74
    /***
    
    -0.73
    <?
    
    -0.71
    POSITIVE LOGITS
     luxuriant
    0.65
     unspeak
    0.63
     unlaw
    0.63
     Inhabitants
    0.61
     whar
    0.61
     maneu
    0.60
    abancı
    0.59
     gaily
    0.58
     indescri
    0.58
     stupendous
    0.58
    Activations Density 1.133%

    No Known Activations