© 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. 2894
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their statistics

    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
    +0.28
    1.1%
    227
    +0.18
    0.7%
    108
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.28
    0.09
    1905
    +0.18
    0.05
    1551
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.51
    }{||
    -0.77
    public
    -0.74
    portál
    -0.72
     onOptions
    -0.69
    lib
    -0.69
    ൊ
    -0.68
    cookieParser
    -0.68
    🎰
    -0.67
    /**
    -0.67
    POSITIVE LOGITS
     accla
    2.36
     affor
    2.32
     depic
    2.29
     reluct
    2.26
     inev
    2.23
     snoopy
    2.22
     Juf
    2.19
     fta
    2.16
     increa
    2.16
     emphat
    2.14
    Activations Density 0.937%

    No Known Activations