© 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. 1720
    Prev
    Next
    INDEX
    Explanations

    specific numeric or code values in data structures

    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
    +0.13
    0.5%
    629
    +0.10
    0.3%
    1978
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.13
    0.06
    1343
    +0.10
    0.06
    138
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.25
     وتسجيلات
    -0.75
    CodeAttribute
    -0.69
     nonatomic
    -0.66
    /***
    
    -0.66
    codehaus
    -0.66
     comprends
    -0.64
    ///**
    -0.63
    twimg
    -0.62
    Πηγές
    -0.61
    POSITIVE LOGITS
     lidl
    0.79
     stockholm
    0.77
     indestru
    0.75
     pandan
    0.73
     anhyd
    0.72
     munich
    0.71
     Silurian
    0.69
     maneu
    0.68
     napoli
    0.68
     frankfurt
    0.68
    Activations Density 0.211%

    No Known Activations