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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14487
    Prev
    Next
    INDEX
    Explanations

    content related to crime reports, burglaries, and city/community announcements

    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
    1491
    +0.15
    0.7%
    687
    +0.15
    0.7%
    1806
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.10
    609
    +0.15
    0.08
    1013
    +0.13
    0.09
    Negative Logits
    <bos>
    -1.19
    /***
    
    -0.65
    
    
    -0.57
     confider
    -0.54
     McKin
    -0.52
    czegó
    -0.49
    /**
    -0.49
    ⓧ
    -0.48
    ///**
    -0.47
     leksikon
    -0.47
    POSITIVE LOGITS
     Anaheim
    0.84
     optik
    0.84
     carrefour
    0.77
     Orlando
    0.76
     pavillon
    0.74
     Anambra
    0.73
     keramik
    0.73
    Orlando
    0.69
     vokal
    0.69
     kram
    0.68
    Activations Density 0.964%

    No Known Activations