© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    recognition of names and notable figures

    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
    +0.14
    0.5%
    1150
    +0.13
    0.5%
    1343
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.14
    0.12
    227
    +0.13
    0.09
    1843
    +0.12
    0.08
    Negative Logits
    <bos>
    -2.34
     himself
    -0.90
     his
    -0.74
     חיצוניים
    -0.73
    ždý
    -0.70
    AnchorTagHelper
    -0.68
     he
    -0.67
     endwhile
    -0.67
     <",
    -0.67
    |}{$
    -0.66
    POSITIVE LOGITS
     maneu
    2.37
     affor
    2.31
     impra
    2.16
     accla
    2.14
     increa
    2.14
     shenan
    2.12
     strick
    2.08
     depic
    2.07
     stockholm
    2.05
     inev
    2.04
    Activations Density 0.369%

    No Known Activations