© 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. 1680
    Prev
    Next
    INDEX
    Explanations

    concepts related to cultural universals and psychological mechanisms

    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
    1.5%
    184
    +0.24
    1.1%
    1842
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.33
    0.08
    876
    +0.24
    -0.02
    184
    +0.19
    0.02
    Negative Logits
    <bos>
    -1.57
     inaugurate
    -0.69
    Jörg
    -0.66
    Pä
    -0.64
    Ár
    -0.61
    Життєпис
    -0.61
    Примеча
    -0.60
    Anar
    -0.60
    AutoScaleMode
    -0.59
     repatri
    -0.59
    POSITIVE LOGITS
     bandung
    1.18
     jaya
    1.13
     jawa
    1.11
     pymysql
    1.09
     heapq
    0.95
    antastic
    0.94
     vrt
    0.93
    jectures
    0.92
     pylab
    0.91
     koni
    0.91
    Activations Density 0.659%

    No Known Activations