© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3767
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to achievements, classifications, and statistical records

    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
    +0.22
    0.9%
    1177
    +0.17
    0.7%
    1842
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.22
    0.07
    766
    +0.17
    0.05
    1403
    +0.14
    0.00
    Negative Logits
    <bos>
    -3.03
    /**
    -1.11
    /**
    -1.10
    /*
    -1.05
    一
    -1.01
    //
    -1.01
    .
    -1.01
    －
    -1.00
    <th>
    -1.00
    <tr>
    -1.00
    POSITIVE LOGITS
     maneu
    4.18
     affor
    4.14
     increa
    4.02
     reluct
    3.99
     shenan
    3.92
     impra
    3.88
     disagre
    3.78
     scrat
    3.65
     emphat
    3.65
     inev
    3.65
    Activations Density 0.941%

    No Known Activations