© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals and entities

    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
    +0.17
    1.0%
    1896
    +0.15
    0.9%
    1124
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.07
    1343
    +0.15
    0.06
    478
    +0.14
    0.04
    Negative Logits
    <bos>
    -2.28
    amaño
    -0.77
    ħħ
    -0.72
    habhar
    -0.69
    ffè
    -0.67
     kuku
    -0.66
    queline
    -0.66
     kark
    -0.62
     kuk
    -0.60
     Crosse
    -0.60
    POSITIVE LOGITS
     McLaugh
    1.21
     Abbé
    1.12
     Shakspeare
    1.06
     Bartholo
    1.03
     McInt
    1.00
     unwarran
    0.97
     increa
    0.95
     vété
    0.94
     Vaugh
    0.94
     impra
    0.93
    Activations Density 0.314%

    No Known Activations