© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    phrases indicating outcomes or consequences, particularly in a negative context

    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
    +0.35
    1.4%
    630
    +0.10
    0.4%
    1253
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.35
    0.04
    630
    +0.10
    0.05
    752
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.87
    /**
    -0.74
    ⓧ
    -0.73
     express
    -0.67
    express
    -0.64
     read
    -0.63
    
    -0.62
    assign
    -0.62
     create
    -0.62
    /*
    -0.62
    POSITIVE LOGITS
     Minang
    1.81
     bandung
    1.77
     Jambi
    1.74
     Palembang
    1.64
     jaya
    1.61
     Karang
    1.60
     Banjar
    1.58
     Juf
    1.57
     Khart
    1.52
     saar
    1.49
    Activations Density 0.340%

    No Known Activations