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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7042
    Prev
    Next
    INDEX
    Explanations

    dates and times mentioned in published materials

    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
    +0.24
    0.9%
    1343
    +0.09
    0.4%
    382
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1040
    +0.24
    0.07
    965
    +0.09
    0.07
    254
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.33
    ⓧ
    -1.49
    
    -1.06
    <?
    -1.04
    /**
    -1.01
    /***
    -0.96
    /*
    -0.95
    <?
    -0.81
    #![
    -0.69
    /*++
    -0.67
    POSITIVE LOGITS
     multicolore
    0.88
     Minang
    0.85
     maroc
    0.85
     cioc
    0.82
     ¡¡
    0.81
     maneu
    0.81
     bandung
    0.79
     jawa
    0.79
     Spani
    0.79
    SBATCH
    0.79
    Activations Density 0.216%

    No Known Activations