© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or relationships among entities

    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
    +0.41
    1.8%
    1967
    +0.10
    0.5%
    1047
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.41
    0.05
    1967
    +0.10
    0.05
    1034
    +0.09
    0.04
    Negative Logits
    <bos>
    -3.00
    ⓧ
    -1.00
    <?
    -0.94
    /**
    -0.93
    /***
    -0.89
    <?
    -0.78
    
    -0.76
    /*!
    -0.70
    /*++
    -0.70
     intersper
    -0.65
    POSITIVE LOGITS
     lemp
    1.35
     lele
    1.35
     kado
    1.19
     bandung
    1.18
     keramik
    1.18
     uhr
    1.17
     kafe
    1.16
     seksi
    1.15
     bambu
    1.14
     kaos
    1.14
    Activations Density 0.310%

    No Known Activations