© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical and wiring components

    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
    +0.30
    1.2%
    876
    +0.14
    0.6%
    1548
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.30
    -0.04
    1415
    +0.14
    0.04
    194
    +0.10
    0.01
    Negative Logits
    <bos>
    -3.61
    ,
    -0.98
    .
    -0.94
    util
    -0.92
     para
    -0.90
    CompleteListener
    -0.90
    div
    -0.88
    Geografía
    -0.88
    echo
    -0.88
    mrow
    -0.87
    POSITIVE LOGITS
     reluct
    3.52
     increa
    3.45
     affor
    3.33
     maneu
    3.33
     shenan
    3.31
     impra
    3.30
     depic
    3.29
     disagre
    3.27
     inev
    3.17
     guarante
    3.16
    Activations Density 1.730%

    No Known Activations