© 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. 5997
    Prev
    Next
    INDEX
    Explanations

    phrases related to demonstrating, showing, or highlighting something to others

    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
    +0.19
    1.1%
    1482
    +0.14
    0.8%
    966
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.19
    0.06
    869
    +0.14
    0.07
    1482
    +0.13
    0.06
    Negative Logits
    <bos>
    -3.13
    
    -0.91
    ⓧ
    -0.91
    <?
    -0.80
    /***
    -0.72
    /**
    -0.71
    <?
    -0.70
    //{
    -0.63
    updateUI
    -0.62
    /*
    -0.61
    POSITIVE LOGITS
    Shows
    1.13
     Showing
    1.12
     Shows
    1.10
     SHOWS
    1.09
     thut
    1.08
     bandung
    1.05
    showing
    1.05
     SHOW
    1.04
    shows
    1.03
     embodi
    1.02
    Activations Density 0.244%

    No Known Activations