© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 300
    Prev
    Next
    INDEX
    Explanations

    references to minimum requirements or rates

    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
    1.0%
    596
    +0.12
    0.6%
    757
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.20
    0.03
    892
    +0.12
    0.03
    971
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.09
    ⓧ
    -0.85
    <?
    -0.81
    /***
    -0.81
    
    -0.77
    Obrázky
    -0.74
    /*!
    -0.72
    ///**
    -0.69
    #![
    -0.64
    <?
    -0.62
    POSITIVE LOGITS
     Minang
    1.21
     santiago
    1.17
     wien
    1.15
     lele
    1.14
     meis
    1.12
     bandung
    1.09
     loto
    1.08
     toscana
    1.08
     sergio
    1.08
     Jambi
    1.07
    Activations Density 0.099%

    No Known Activations