© 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. 1561
    Prev
    Next
    INDEX
    Explanations

    directives related to communication and interactions involving personal and intimate subjects

    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
    0.9%
    1150
    +0.09
    0.3%
    1166
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.26
    0.05
    448
    +0.09
    0.04
    1352
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.89
    /***
    -0.72
    endwhile
    -0.66
    })();
    -0.64
    Kontrola
    -0.64
    //---
    -0.63
    didSet
    -0.63
    /*@
    -0.61
    displayquote
    -0.60
    ⓧ
    -0.59
    POSITIVE LOGITS
     pymysql
    1.22
     smtplib
    1.19
     soulign
    1.09
     Manufact
    0.99
     Minang
    0.98
     véhic
    0.98
     considér
    0.96
     pylab
    0.96
     Ename
    0.96
    dison
    0.90
    Activations Density 0.536%

    No Known Activations