© 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. 1274
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection and inquiry

    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
    +0.26
    0.9%
    381
    +0.09
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.26
    0.04
    872
    +0.09
    0.06
    607
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.41
    <?
    -0.67
    estimable
    -0.64
    ⓧ
    -0.63
    
    -0.62
    новниш
    -0.62
    FunctionFlags
    -0.60
    RTDA
    -0.58
    bited
    -0.56
     auton
    -0.55
    POSITIVE LOGITS
     soulign
    1.05
     maneu
    0.92
     shenan
    0.85
     pylab
    0.82
     véhic
    0.82
     vété
    0.80
     unlaw
    0.79
     récomp
    0.78
     accla
    0.77
     depic
    0.77
    Activations Density 0.495%

    No Known Activations