© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    phrases that express challenges or harsh realities

    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
    +0.31
    1.1%
    2034
    +0.09
    0.3%
    1980
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2034
    +0.31
    0.09
    1055
    +0.09
    0.06
    1163
    +0.07
    0.06
    Negative Logits
    <bos>
    -2.04
    ⓧ
    -0.87
    /**
    -0.73
    
    -0.72
    /*!
    -0.70
    /*++
    -0.70
    /***
    -0.70
    //});
    -0.66
    <?
    -0.65
     intersper
    -0.65
    POSITIVE LOGITS
     but
    0.98
    but
    0.89
     But
    0.89
     nhưng
    0.85
     BUT
    0.85
    But
    0.84
     cartier
    0.81
     pero
    0.81
     signora
    0.80
     Hitam
    0.78
    Activations Density 0.843%

    No Known Activations