© 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. 4755
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics presented in a text

    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
    0.9%
    1964
    +0.15
    0.8%
    1978
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.17
    0.06
    1343
    +0.15
    0.05
    1964
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.52
    <?
    -0.76
     дописавши
    -0.73
    /***
    -0.72
    <?
    -0.72
    //---
    -0.65
     intersper
    -0.64
     overcrow
    -0.63
    Ķ
    -0.63
    frastructure
    -0.59
    POSITIVE LOGITS
     jaya
    0.85
     susun
    0.79
     muna
    0.78
     jawa
    0.77
     jati
    0.73
     bagay
    0.71
     tanong
    0.70
     kani
    0.70
     guma
    0.68
     makam
    0.68
    Activations Density 0.106%

    No Known Activations