© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1339
    Prev
    Next
    INDEX
    Explanations

    musical terms and chord progressions

    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
    1.0%
    1842
    +0.14
    0.6%
    906
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.22
    0.04
    488
    +0.14
    0.03
    1596
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.71
    styleType
    -1.04
     Roskov
    -0.96
    contentLoaded
    -0.96
     NSCoder
    -0.96
    ByVersion
    -0.95
    ScopeManager
    -0.95
    ISupport
    -0.95
    titleMargin
    -0.95
    PerformLayout
    -0.94
    POSITIVE LOGITS
     increa
    2.75
     maneu
    2.68
     affor
    2.63
     disagre
    2.56
     impra
    2.50
     disreg
    2.49
     shenan
    2.49
     reluct
    2.44
     emphat
    2.43
     inev
    2.35
    Activations Density 0.248%

    No Known Activations