© 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. 340
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction with governmental authority and its actions

    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
    +0.32
    1.2%
    604
    +0.16
    0.6%
    198
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1784
    +0.32
    0.07
    804
    +0.16
    0.05
    764
    +0.07
    0.03
    Negative Logits
    <bos>
    -3.51
    /***
    -0.58
     Normdatei
    -0.57
    Referències
    -0.56
     الرياضيه
    -0.56
    ///**
    -0.55
     recover
    -0.55
     evacuate
    -0.55
     autorytatywna
    -0.55
     liberate
    -0.54
    POSITIVE LOGITS
     embodi
    1.08
     paradiso
    1.08
     soggior
    1.00
     Palembang
    0.95
     dott
    0.92
     riva
    0.92
     tramont
    0.91
     marea
    0.91
     Minang
    0.90
     Almería
    0.90
    Activations Density 1.365%

    No Known Activations