© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1429
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mention" and its variations

    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
    +0.25
    1.4%
    313
    +0.11
    0.6%
    31
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.25
    0.02
    899
    +0.11
    0.02
    313
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.88
    ⓧ
    -0.94
    <?
    
    -0.74
    /*++
    -0.73
    /**
    -0.71
    Ligações
    -0.69
    <?
    -0.69
    //{
    
    -0.68
    public
    -0.67
    fristi
    -0.67
    POSITIVE LOGITS
     affor
    1.90
     thut
    1.90
     maneu
    1.87
     squa
    1.78
     increa
    1.78
     inev
    1.75
     volunte
    1.73
     Juf
    1.73
     fta
    1.72
     Minang
    1.71
    Activations Density 0.057%

    No Known Activations