© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    references to a specific person, particularly the name "Lau."

    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
    1334
    +0.17
    1.0%
    1515
    +0.12
    0.7%
    1520
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.04
    1334
    +0.12
    0.03
    227
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.54
     ķ
    -0.67
     liel
    -0.62
     ģ
    -0.62
    移
    -0.60
     ļ
    -0.60
     bēr
    -0.58
     vēl
    -0.57
     dzī
    -0.56
     support
    -0.54
    POSITIVE LOGITS
     increa
    1.45
     ftu
    1.40
     auri
    1.39
     squa
    1.35
     scrat
    1.35
     maneu
    1.34
     indestru
    1.33
     excru
    1.30
     miu
    1.29
     paula
    1.28
    Activations Density 0.181%

    No Known Activations