© 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. 5120
    Prev
    Next
    INDEX
    Explanations

    punctuation or periods at the end of sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.3%
    382
    +0.14
    0.7%
    1535
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    842
    +0.27
    0.04
    1894
    +0.14
    0.03
    1686
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.51
     intersper
    -0.95
     endow
    -0.90
     disambigu
    -0.85
     reconno
    -0.72
     gratify
    -0.72
     forbear
    -0.72
     blanch
    -0.71
    ⓧ
    -0.70
     amass
    -0.70
    POSITIVE LOGITS
     seksi
    1.02
    Literat
    0.82
     keramik
    0.81
     karton
    0.77
     kafe
    0.76
     silikon
    0.76
     optik
    0.74
     kompres
    0.72
     kalori
    0.71
     induk
    0.70
    Activations Density 0.090%

    No Known Activations