© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    phrases indicating benefit or advantage

    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
    +0.30
    1.2%
    1527
    +0.11
    0.4%
    501
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.30
    0.03
    1507
    +0.11
    0.03
    1052
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.05
    databind
    -0.78
     initComponents
    -0.76
    CreateMap
    -0.74
    stringify
    -0.71
    unmodifiable
    -0.71
    ("}");
    -0.70
    BeginInit
    -0.70
    quad
    -0.69
    core
    -0.69
    POSITIVE LOGITS
     increa
    2.15
     maneu
    2.07
     guarante
    1.99
     impra
    1.98
     shenan
    1.95
     stockholm
    1.93
     affor
    1.90
     scrat
    1.90
     intermitt
    1.89
     inev
    1.89
    Activations Density 0.248%

    No Known Activations