© 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. 4865
    Prev
    Next
    INDEX
    Explanations

    terms related to academic publishing and permissions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    184
    +0.43
    2.1%
    1343
    +0.36
    1.7%
    764
    +0.32
    1.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.43
    0.10
    184
    +0.36
    0.03
    764
    +0.32
    0.05
    Negative Logits
    <bos>
    -2.38
    Personendaten
    -1.04
     ویکی‌پدی
    -1.00
    Autoritní
    -0.99
    ⓧ
    -0.94
    /**
    -0.83
    
    -0.82
     Савезне
    -0.81
     Мексичка
    -0.81
    Билгалдахарш
    -0.81
    POSITIVE LOGITS
    :"-
    0.75
    ">.
    0.64
    !")
    0.58
    ...");
    0.58
    ".
    0.57
     durs
    0.56
    >"+
    0.56
     adal
    0.55
    "]).
    0.55
    :{
    0.55
    Activations Density 0.315%

    No Known Activations