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. 1136
    Prev
    Next
    INDEX
    Explanations

    nouns related to roles and functions in programming or technology

    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
    +0.15
    0.7%
    966
    +0.13
    0.6%
    1363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.08
    1870
    +0.13
    0.05
    484
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.27
    /***
    
    -0.66
    ///**
    -0.62
     fortsetter
    -0.61
    displayquote
    -0.60
    ///////////////
    -0.59
    RunAsync
    -0.59
    Kanpo
    -0.56
    increments
    -0.56
    djangoproject
    -0.55
    POSITIVE LOGITS
     saar
    1.22
     riviera
    1.16
     alha
    1.12
     territo
    1.09
     stockholm
    1.09
     Minang
    1.08
     naer
    1.07
     impra
    1.04
     Czechos
    1.04
     maksi
    1.03
    Activations Density 0.609%

    No Known Activations