© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related terminology

    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%
    939
    +0.09
    0.3%
    1018
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1879
    +0.24
    0.03
    876
    +0.09
    -0.00
    1343
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.61
    Vegeu
    -0.83
    ⓧ
    -0.81
     here
    -0.79
      
    -0.75
     and
    -0.73
     for
    -0.72
     into
    -0.71
    ,
    -0.70
     lombok
    -0.70
    POSITIVE LOGITS
     napoli
    2.21
     stockholm
    2.18
     wien
    2.11
     bandung
    2.10
     affor
    2.10
     haup
    2.05
     emphat
    2.04
     bordeaux
    2.02
     lidl
    2.00
     peppa
    2.00
    Activations Density 0.138%

    No Known Activations