© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 387
    Prev
    Next
    INDEX
    Explanations

    phrases related to sending messages or communications

    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
    +0.26
    1.4%
    1178
    +0.11
    0.6%
    849
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.26
    0.04
    1451
    +0.11
    0.04
    991
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.83
    struct
    -0.67
    hyrchwyd
    -0.67
    //[
    -0.66
    HasAnnotation
    -0.66
    /*
    -0.65
    stra
    -0.65
    log
    -0.65
    ln
    -0.64
    itemize
    -0.64
    POSITIVE LOGITS
     increa
    2.13
     impra
    2.06
     reluct
    2.04
     emphat
    2.03
     affor
    2.02
     disagre
    2.01
     indestru
    2.00
     unden
    2.00
     maneu
    1.97
     accla
    1.94
    Activations Density 0.096%

    No Known Activations