© 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. 113
    Prev
    Next
    INDEX
    Explanations

    references to groups of people involved in significant events or discussions

    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%
    1363
    +0.10
    0.4%
    1510
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.24
    0.07
    990
    +0.10
    0.06
    1510
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.40
     solidar
    -1.02
     dras
    -1.00
    /***
    -0.92
     utop
    -0.89
     geograf
    -0.87
     /**
    -0.87
     ideolog
    -0.84
     abstra
    -0.83
     impon
    -0.82
    POSITIVE LOGITS
     unspeak
    1.11
     disreg
    1.10
     unwarran
    1.08
     impractica
    1.05
     unlaw
    1.05
     indestru
    1.05
     caucasian
    1.00
     cuck
    1.00
     ingrat
    0.97
     pamph
    0.97
    Activations Density 0.439%

    No Known Activations