Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1791
    Prev
    Next
    INDEX
    Explanations

    references to global contexts or international issues

    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
    +0.32
    1.5%
    2034
    +0.15
    0.7%
    1828
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.32
    0.04
    1376
    +0.15
    0.04
    1296
    +0.09
    0.04
    Negative Logits
    <bos>
    -3.07
    /***
    
    -0.68
    //{
    
    -0.61
     rehabilitate
    -0.57
     EconPapers
    -0.57
     manage
    -0.56
     mitigate
    -0.56
    //@
    -0.55
     inaugurate
    -0.55
    ɵɵelement
    -0.54
    POSITIVE LOGITS
     ecru
    1.47
     bordeaux
    1.35
     chrysler
    1.23
     outlander
    1.20
     unwarran
    1.19
     madonna
    1.19
     lele
    1.19
     unlaw
    1.18
     lamborghini
    1.18
     paradiso
    1.17
    Activations Density 0.113%

    No Known Activations