© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the"

    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
    +0.44
    2.3%
    1741
    +0.17
    0.9%
    1385
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.44
    0.11
    1385
    +0.17
    0.11
    1741
    +0.15
    0.01
    Negative Logits
    <bos>
    -2.98
    ,
    -0.58
    <eos>
    -0.56
     and
    -0.56
    /
    -0.56
     kasarigan
    -0.55
    Referències
    -0.54
    .
    -0.54
    ↵↵
    -0.54
     had
    -0.52
    POSITIVE LOGITS
     Áng
    1.38
     bandung
    1.30
     swarovski
    1.29
     Minang
    1.28
     Darío
    1.27
     santiago
    1.25
     Haci
    1.24
     Valentín
    1.21
     valencia
    1.20
     véhic
    1.19
    Activations Density 1.028%

    No Known Activations