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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 730
    Prev
    Next
    INDEX
    Explanations

    references to natural or environmental resources

    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
    1.7%
    1870
    +0.14
    0.9%
    1140
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1140
    +0.28
    0.02
    1763
    +0.14
    0.02
    990
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.71
    /***
    
    -0.83
    ⓧ
    -0.79
     inaugurate
    -0.74
    <?
    -0.72
    /**
    -0.69
    
    
    -0.67
    <?
    
    -0.66
    //---
    -0.65
     abolish
    -0.65
    POSITIVE LOGITS
     jaya
    1.28
     jawa
    1.27
     bandung
    1.25
     resources
    1.22
     lele
    1.19
     resource
    1.18
     RESOURCE
    1.12
     Resources
    1.12
     Resource
    1.09
     RESOURCES
    1.07
    Activations Density 0.036%

    No Known Activations