© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2135
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "draft" 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
    +0.22
    1.2%
    1101
    +0.13
    0.7%
    1961
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.22
    0.03
    316
    +0.13
    0.03
    1562
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.42
    CodeDom
    -0.69
    mbggenerated
    -0.65
    IonicModule
    -0.64
    ComponentModel
    -0.62
    |}
    -0.61
    addComponent
    -0.59
    Object
    -0.58
    SizeMode
    -0.58
    glEnable
    -0.56
    POSITIVE LOGITS
     affor
    1.49
     maroc
    1.43
     impra
    1.31
     maneu
    1.31
     Minang
    1.31
     jati
    1.28
     stockholm
    1.27
     accla
    1.27
     increa
    1.27
     emphat
    1.27
    Activations Density 0.040%

    No Known Activations