© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    calls to action regarding governmental policies and legislation

    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
    +0.34
    1.2%
    764
    +0.07
    0.2%
    1510
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1563
    +0.34
    0.06
    1768
    +0.07
    0.05
    1352
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.79
    /***
    -1.12
     intersper
    -0.97
    ⓧ
    -0.96
    //*/
    -0.87
    
    -0.85
    //---
    -0.81
    //...
    -0.81
    /*!
    -0.80
     disbur
    -0.80
    POSITIVE LOGITS
     montagna
    0.70
    GYPT
    0.69
     Minang
    0.67
     Jambi
    0.62
    requipa
    0.62
     borderRadius
    0.61
    spectos
    0.60
     jawa
    0.60
     soulign
    0.59
     pagkak
    0.59
    Activations Density 0.805%

    No Known Activations