© 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. 1409
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or references to significant characters in the text

    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
    +0.16
    0.5%
    1539
    +0.08
    0.3%
    1288
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.10
    1978
    +0.08
    0.08
    483
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.40
    ///**
    -0.71
    /***
    -0.70
     mergeFrom
    -0.69
    ⏪
    -0.67
    InSection
    -0.67
     ExecuteAsync
    -0.64
    /*!
    -0.63
    IsMutable
    -0.63
     gynnwys
    -0.63
    POSITIVE LOGITS
     shenan
    1.84
     disagre
    1.73
     maneu
    1.72
     affor
    1.69
     snoopy
    1.61
     impra
    1.60
     uninten
    1.59
     increa
    1.57
     unspeak
    1.53
     excru
    1.52
    Activations Density 0.750%

    No Known Activations