© 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. 430
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and interactive platforms

    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
    +0.28
    1.1%
    764
    +0.10
    0.4%
    227
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.28
    0.06
    227
    +0.10
    0.07
    1799
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.45
    /**
    -0.79
    /*++
    -0.79
    SequentialGroup
    -0.77
    Sqft
    -0.75
    <?
    
    -0.73
     viewWillAppear
    -0.70
    <?
    -0.69
    ɵɵ
    -0.69
    ValueGeneration
    -0.69
    POSITIVE LOGITS
     maneu
    1.91
     affor
    1.80
     shenan
    1.79
     impra
    1.72
     reluct
    1.69
     increa
    1.69
     disagre
    1.68
     excru
    1.62
     accla
    1.59
     uninten
    1.57
    Activations Density 0.547%

    No Known Activations