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. 824
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced computing and technology deployment

    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
    1.2%
    1870
    +0.18
    0.7%
    678
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.28
    0.08
    1385
    +0.18
    0.09
    678
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.50
    /***
    
    -0.75
    /*++
    -0.75
    <?
    -0.65
    HasAnnotation
    -0.64
    else
    -0.61
    DataPropertyName
    -0.61
    /*!
    
    -0.61
    HasColumnType
    -0.59
    /**
    -0.57
    POSITIVE LOGITS
     bandung
    1.66
     Minang
    1.42
     paradiso
    1.40
     lele
    1.35
     prado
    1.35
     jawa
    1.34
     sentra
    1.33
     milano
    1.32
     riva
    1.29
     palio
    1.26
    Activations Density 0.740%

    No Known Activations