© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 53
    Prev
    Next
    INDEX
    Explanations

    instances of the word "about"

    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
    +0.25
    1.4%
    1757
    +0.15
    0.8%
    1506
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1506
    +0.25
    0.05
    1757
    +0.15
    0.05
    25
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.52
    /**
    -0.71
    ⓧ
    -0.65
    /*++
    -0.60
    /***
    
    -0.58
    aux
    -0.56
    cal
    -0.56
    ver
    -0.56
     Gar
    -0.56
    Contras
    -0.56
    POSITIVE LOGITS
     bandung
    1.48
     maroc
    1.38
     milano
    1.37
     bordeaux
    1.35
     cioc
    1.34
     Minang
    1.30
     venuto
    1.29
     paradiso
    1.29
     napoli
    1.28
     ibiza
    1.28
    Activations Density 0.109%

    No Known Activations