© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4760
    Prev
    Next
    INDEX
    Explanations

    references to specific dates

    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
    1896
    +0.16
    0.7%
    281
    +0.12
    0.5%
    442
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.16
    0.04
    499
    +0.12
    0.04
    1267
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.68
    <?
    -0.94
    ⓧ
    -0.91
    
    -0.82
     rehabilitate
    -0.65
    /**
    -0.64
     stifle
    -0.61
     triumphed
    -0.59
     cooperated
    -0.58
     persevere
    -0.58
    POSITIVE LOGITS
     soulign
    1.14
     véhic
    1.08
     délib
    1.02
     considér
    1.01
     catég
    0.98
     quoique
    0.94
     Eqs
    0.94
     réput
    0.94
     alté
    0.93
     éto
    0.92
    Activations Density 0.037%

    No Known Activations