© 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. 252
    Prev
    Next
    INDEX
    Explanations

    references to institutions and organizations related to atmospheric studies

    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
    851
    +0.15
    0.6%
    629
    +0.13
    0.6%
    1343
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.08
    227
    +0.13
    0.07
    190
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.74
    inglés
    -0.63
     trail
    -0.63
     hit
    -0.60
     продаже
    -0.58
    /**
    -0.56
     рано
    -0.56
    
    -0.56
     led
    -0.56
     miesięcy
    -0.56
    POSITIVE LOGITS
     dises
    1.42
     thut
    1.36
     tramont
    1.33
     gend
    1.26
     inev
    1.25
     trion
    1.18
     lill
    1.17
     Sén
    1.17
     alre
    1.17
     frow
    1.16
    Activations Density 0.364%

    No Known Activations