© 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. 303
    Prev
    Next
    INDEX
    Explanations

    references to different gaming consoles and their respective versions

    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
    +0.27
    1.1%
    1741
    +0.10
    0.4%
    1870
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1798
    +0.27
    0.03
    121
    +0.10
    0.02
    1589
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.67
    /**
    -0.94
    ⓧ
    -0.91
    <?
    -0.82
    
    -0.78
    /***
    -0.76
     springfox
    -0.65
    ///**
    -0.65
    InjectMocks
    -0.62
    <?
    -0.61
    POSITIVE LOGITS
     epoca
    0.89
     paradiso
    0.85
     ecru
    0.84
     montagna
    0.80
     malheureux
    0.79
     riva
    0.79
     excès
    0.78
     épu
    0.76
     nobile
    0.76
     déchir
    0.74
    Activations Density 0.062%

    No Known Activations