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. 1004
    Prev
    Next
    INDEX
    Explanations

    references to specific soccer teams, particularly FC Cincinnati and FC Dallas

    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
    +0.21
    1.2%
    597
    +0.14
    0.8%
    492
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.21
    0.02
    276
    +0.14
    0.02
    597
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.21
    
    
    -0.82
     springfox
    -0.68
     Roskov
    -0.67
    /**
    -0.65
     viewWillAppear
    -0.64
    ftagPool
    -0.61
     Bourgoin
    -0.59
    <?
    -0.59
    पया
    -0.57
    POSITIVE LOGITS
     FC
    1.22
    FC
    1.09
     fc
    0.97
    fc
    0.90
     véhic
    0.81
     Glou
    0.78
     Vaugh
    0.77
     Haci
    0.75
    Terminology
    0.75
     Fc
    0.74
    Activations Density 0.067%

    No Known Activations