© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 411
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or ability

    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
    +0.25
    1.2%
    1839
    +0.10
    0.5%
    1806
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.25
    0.03
    1839
    +0.10
    0.03
    1047
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.80
    /***
    
    -0.64
    EndProject
    -0.58
     harmonize
    -0.57
     expel
    -0.57
     enshr
    -0.56
    /**
    -0.56
     intersper
    -0.55
     banish
    -0.55
    ///**
    -0.55
    POSITIVE LOGITS
     saar
    1.01
    Able
    0.99
     kafe
    0.99
     cannes
    0.94
     ananas
    0.93
     silikon
    0.93
     seksi
    0.92
     tyn
    0.91
     tramont
    0.90
     Muhamma
    0.90
    Activations Density 0.040%

    No Known Activations