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. 1883
    Prev
    Next
    INDEX
    Explanations

    references to player performance and statistics in sports

    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
    +0.28
    1.1%
    1253
    +0.10
    0.4%
    108
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.28
    0.08
    1905
    +0.10
    0.07
    736
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.19
    #
    -0.70
    /***
    
    -0.63
    }{||
    -0.62
    contentLoaded
    -0.61
    },[])
    -0.57
    
    
    -0.56
    /*
    -0.56
    //
    -0.56
    public
    -0.56
    POSITIVE LOGITS
     uhr
    1.27
     accla
    1.23
     applau
    1.15
     saar
    1.14
     Lombar
    1.12
     riviera
    1.09
     vost
    1.08
     sembl
    1.07
     incess
    1.06
     wattpad
    1.05
    Activations Density 0.953%

    No Known Activations