© 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. 318
    Prev
    Next
    INDEX
    Explanations

    technical terms related to CUDA programming and memory management

    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
    453
    +0.29
    1.1%
    1343
    +0.14
    0.5%
    184
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.29
    0.06
    1343
    +0.14
    0.05
    876
    +0.10
    -0.00
    Negative Logits
    <bos>
    -2.42
    /**
    -1.06
    ⓧ
    -1.01
    /*
    -0.98
    
    
    -0.89
     AssemblyCompany
    -0.81
    InstrumentedTest
    -0.77
    JspWriter
    -0.76
    ,
    -0.76
     by
    -0.70
    POSITIVE LOGITS
    !!</
    1.50
     ordina
    1.44
     doman
    1.42
     milano
    1.40
     incess
    1.40
     marte
    1.38
     ciga
    1.38
     toul
    1.38
     meis
    1.36
     maroc
    1.35
    Activations Density 0.146%

    No Known Activations