© 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. 3010
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective and statements of intent or feeling

    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
    +0.37
    2.1%
    478
    +0.14
    0.8%
    381
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    920
    +0.37
    0.06
    658
    +0.14
    0.06
    479
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.67
    ///**
    -0.59
    HasIndex
    -0.54
    public
    -0.52
    /**
    -0.52
     itself
    -0.52
     gela
    -0.51
    col
    -0.51
    fektions
    -0.51
    ുറ
    -0.50
    POSITIVE LOGITS
     accla
    1.22
     unlaw
    1.17
     increa
    1.17
     Minang
    1.16
     viciss
    1.15
     disagre
    1.14
     depic
    1.12
     reluct
    1.11
     perfet
    1.11
     inev
    1.11
    Activations Density 0.096%

    No Known Activations