© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 3238
    Prev
    Next
    INDEX
    Explanations

    references to numbers and counts related to experiences or transactions

    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
    +0.33
    1.6%
    1699
    +0.08
    0.4%
    776
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.33
    0.03
    1925
    +0.08
    0.03
    776
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.72
     intersper
    -0.95
    ⓧ
    -0.95
     quitted
    -0.90
     disbur
    -0.89
     endow
    -0.82
     amass
    -0.81
    
    
    -0.80
    /***
    
    -0.77
     superintend
    -0.77
    POSITIVE LOGITS
     maroc
    0.80
     AssemblyCulture
    0.74
     bandung
    0.72
     Désolé
    0.72
     kafe
    0.70
     balon
    0.70
     ananas
    0.70
     jawa
    0.69
     contextLoads
    0.69
     cioc
    0.68
    Activations Density 0.062%

    No Known Activations