© 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. 370
    Prev
    Next
    INDEX
    Explanations

    references to physical activity and daily routines

    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
    +0.32
    1.3%
    1013
    +0.25
    1.0%
    381
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.32
    0.13
    946
    +0.25
    0.07
    1166
    +0.12
    0.06
    Negative Logits
    <bos>
    -1.89
     modernize
    -0.62
     thrived
    -0.59
    qiao
    -0.59
     coexist
    -0.57
     endow
    -0.55
     abolish
    -0.54
     rehabilitate
    -0.54
     unify
    -0.53
     flourished
    -0.53
    POSITIVE LOGITS
     Minang
    0.82
     Jambi
    0.78
     fusca
    0.78
     Pekan
    0.75
     Muhamma
    0.73
     panik
    0.72
     Palembang
    0.72
     tomat
    0.71
    cepan
    0.70
    échal
    0.70
    Activations Density 1.233%

    No Known Activations