© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1960
    Prev
    Next
    INDEX
    Explanations

    references to studies and research

    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
    +0.28
    1.7%
    241
    +0.13
    0.8%
    2011
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.28
    0.04
    241
    +0.13
    0.04
    2011
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.96
    찮
    -0.68
    র্ব
    -0.66
    printf
    -0.62
    ുറ
    -0.61
     AssemblyCompany
    -0.61
    rungsseite
    -0.60
    else
    -0.59
     mit
    -0.59
     државе
    -0.59
    POSITIVE LOGITS
     increa
    2.08
     maneu
    2.08
     unlaw
    2.07
     unwarran
    2.00
     impra
    1.98
     affor
    1.96
     accla
    1.90
     guarante
    1.89
     disagre
    1.88
     strick
    1.85
    Activations Density 0.067%

    No Known Activations