© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    instances of the word "now" occurring in a text

    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
    1.3%
    1742
    +0.12
    0.6%
    1671
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1742
    +0.24
    0.09
    1671
    +0.12
    0.07
    47
    +0.11
    0.06
    Negative Logits
    <bos>
    -3.35
    export
    -0.63
    Kontrola
    -0.61
    beans
    -0.61
    import
    -0.61
    public
    -0.61
    commit
    -0.60
    円
    -0.58
    SequentialGroup
    -0.58
    interface
    -0.58
    POSITIVE LOGITS
     affor
    1.85
     maneu
    1.85
     unlaw
    1.74
     accla
    1.68
     hairc
    1.68
     stockholm
    1.66
     emphat
    1.63
     lidl
    1.62
     lamborghini
    1.61
     disreg
    1.60
    Activations Density 0.279%

    No Known Activations