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

    Neuronpedia

    Jacobian LensNEW
    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. 2539
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions or grievances

    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
    +0.24
    0.9%
    1870
    +0.10
    0.3%
    1372
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.24
    0.07
    332
    +0.10
    0.05
    1553
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.14
     intersper
    -1.50
     encomp
    -1.38
     fuf
    -1.33
     emphat
    -1.17
     ?...
    -1.15
     forbear
    -1.13
     depic
    -1.13
     quitted
    -1.10
     !...
    -1.09
    POSITIVE LOGITS
     pylab
    1.01
     heapq
    0.97
     pymysql
    0.91
     pymongo
    0.83
     smtplib
    0.74
     hashlib
    0.71
    gruntled
    0.71
     ferdig
    0.69
     ameste
    0.69
     OrderedDict
    0.68
    Activations Density 0.425%

    No Known Activations