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. 6-RES-JB
    6. 60
    Prev
    Next
    INDEX
    Explanations

    questions or statements regarding uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.9%
    1376
    +0.12
    0.5%
    220
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.20
    0.06
    1376
    +0.12
    0.05
    581
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -0.83
    /**
    -0.80
    /*
    -0.74
    
    
    -0.73
    /***
    
    -0.73
    #
    -0.73
    <?
    -0.70
    ///**
    -0.67
    #![
    -0.67
    POSITIVE LOGITS
     Juf
    1.83
     ftu
    1.74
     aen
    1.71
     thut
    1.67
     fta
    1.65
     fays
    1.64
     fortn
    1.64
     maneu
    1.62
     sovere
    1.60
     ftre
    1.60
    Activations Density 0.376%

    No Known Activations