© 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. 102
    Prev
    Next
    INDEX
    Explanations

    the word "mere" or its derivatives, indicating a focus on trivialization or insignificance

    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
    +0.24
    1.2%
    61
    +0.12
    0.6%
    1520
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.24
    0.02
    1520
    +0.12
    0.02
    1981
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.48
    cout
    -0.72
    CreateMap
    -0.70
    public
    -0.67
    class
    -0.65
    start
    -0.64
    lat
    -0.63
    WriteLiteral
    -0.63
    back
    -0.63
    set
    -0.62
    POSITIVE LOGITS
     ecru
    1.68
     swarovski
    1.52
     lamborghini
    1.52
     frankfurt
    1.51
     chrysler
    1.49
     munich
    1.49
     venice
    1.49
     jorge
    1.49
     javier
    1.49
     roberto
    1.48
    Activations Density 0.029%

    No Known Activations