© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3022
    Prev
    Next
    INDEX
    Explanations

    references to shared experiences or collective actions

    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
    1.1%
    1124
    +0.12
    0.5%
    1404
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.28
    0.03
    1124
    +0.12
    0.02
    276
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.98
    tag
    -0.56
    듬
    -0.54
    public
    -0.54
    object
    -0.51
    렵
    -0.51
    ソッド
    -0.50
    bot
    -0.50
    age
    -0.50
     розта
    -0.50
    POSITIVE LOGITS
     guarante
    1.17
     whil
    1.08
     chrysler
    1.08
     accla
    1.05
     maneu
    1.03
     inev
    1.00
     affor
    1.00
     Muhamma
    0.99
     Somal
    0.98
     Juf
    0.97
    Activations Density 0.141%

    No Known Activations