© 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. 476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating objectives or purposes in a study or document

    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
    +0.37
    1.4%
    1506
    +0.09
    0.3%
    1573
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1513
    +0.37
    0.03
    752
    +0.09
    0.04
    92
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.84
    ,
    -0.86
    .
    -0.86
    ;
    -0.79
     and
    -0.77
    /**
    -0.74
    。
    -0.69
    '
    -0.68
    {
    -0.68
    、
    -0.67
    POSITIVE LOGITS
     affor
    2.10
     increa
    2.10
     accla
    2.06
     reluct
    2.05
     inev
    2.00
     maneu
    1.94
     disagre
    1.94
     ftu
    1.93
     fta
    1.92
     perfet
    1.88
    Activations Density 0.281%

    No Known Activations