© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to statistics or counts

    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
    +0.30
    1.4%
    776
    +0.14
    0.7%
    1978
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.30
    0.09
    573
    +0.14
    0.09
    321
    +0.13
    0.08
    Negative Logits
    <bos>
    -2.80
    ⓧ
    -0.69
     evacuate
    -0.68
     rehabilitate
    -0.68
     retain
    -0.66
     restore
    -0.66
     prepare
    -0.65
     mobilize
    -0.64
     adopt
    -0.63
    #![
    -0.63
    POSITIVE LOGITS
     maksi
    1.42
     antik
    1.39
     silikon
    1.39
     mikrofon
    1.38
     kafe
    1.37
     keramik
    1.35
     optik
    1.32
     seksi
    1.30
     Ferdin
    1.29
     Keny
    1.26
    Activations Density 0.174%

    No Known Activations