© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2725
    Prev
    Next
    INDEX
    Explanations

    sentences expressing the value or implications of an experience or situation

    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
    +0.20
    0.8%
    2034
    +0.15
    0.6%
    1013
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.20
    0.08
    1013
    +0.15
    0.10
    284
    +0.11
    0.08
    Negative Logits
    <bos>
    -2.47
    /***
    -0.89
    Fuckin
    -0.82
    ⓧ
    -0.82
    <?
    -0.79
    Yeet
    -0.78
    #![
    -0.77
    
    -0.74
    /**
    -0.73
    Lma
    -0.72
    POSITIVE LOGITS
     kaos
    1.17
     lele
    1.09
     panik
    1.05
     silikon
    1.03
     seksi
    1.03
     kasa
    1.03
     jawa
    1.02
     bandung
    1.02
     kafe
    1.01
     kade
    0.99
    Activations Density 0.710%

    No Known Activations