© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1462
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    +0.31
    1.3%
    2019
    +0.12
    0.5%
    122
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.31
    0.04
    1049
    +0.12
    0.03
    351
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -0.88
    /***
    -0.82
     gratify
    -0.82
     quitted
    -0.80
    <?
    -0.77
     forbear
    -0.75
     intersper
    -0.74
    <?
    -0.72
     disbur
    -0.72
    POSITIVE LOGITS
     Heeren
    0.78
     laboratorium
    0.71
     Ferdin
    0.70
     Spani
    0.69
     Teknik
    0.68
     Medan
    0.65
     Præ
    0.64
     Pekan
    0.63
     Wednesday
    0.63
     Tuesday
    0.62
    Activations Density 0.164%

    No Known Activations