© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    references to the word "great" and its variants in various contexts

    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
    +0.24
    1.4%
    994
    +0.11
    0.6%
    755
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.24
    0.03
    755
    +0.11
    0.04
    1573
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.73
    //
    -0.60
    public
    -0.56
    enumerate
    -0.56
    Autoritní
    -0.56
    
    -0.55
    cd
    -0.54
    ⓧ
    -0.54
     send
    -0.54
    <td>
    -0.53
    POSITIVE LOGITS
     santiago
    1.40
     Minang
    1.39
     milano
    1.38
     napoli
    1.38
     ecru
    1.31
     tupperware
    1.29
     sappi
    1.28
     felipe
    1.28
     dott
    1.28
     peppa
    1.26
    Activations Density 0.057%

    No Known Activations