© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    situations involving surprise or unexpected interactions

    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
    +0.26
    1.0%
    1842
    +0.17
    0.7%
    876
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    792
    +0.26
    0.04
    876
    +0.17
    -0.02
    1284
    +0.14
    0.05
    Negative Logits
    <bos>
    -3.17
    DoubleQuotes
    -1.03
    Enllaços
    -0.95
     <>",
    -0.87
    BUYER
    -0.85
    public
    -0.85
    UnitTesting
    -0.84
    Unmarshaller
    -0.84
    SourceChecksum
    -0.84
    WriteLiteral
    -0.82
    POSITIVE LOGITS
     affor
    2.98
     maneu
    2.70
     stockholm
    2.65
     reluct
    2.62
     increa
    2.59
     disagre
    2.57
     impra
    2.57
     accla
    2.55
     emphat
    2.52
     inev
    2.52
    Activations Density 0.451%

    No Known Activations