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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2021
    Prev
    Next
    INDEX
    Explanations

    descriptions related to historical periods

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.5%
    1806
    +0.06
    0.3%
    776
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1123
    +0.11
    0.04
    1728
    +0.06
    0.04
    929
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.74
    public
    -0.72
    ///**
    -0.70
    ⓧ
    -0.69
    ///
    -0.65
    ਿੱ
    -0.64
    <?
    -0.64
    //
    -0.63
    /**
    -0.61
    //@
    -0.60
    POSITIVE LOGITS
     maneu
    1.74
     period
    1.71
     Period
    1.65
     Periods
    1.65
     affor
    1.64
     véhic
    1.62
     Juf
    1.55
    Periods
    1.53
    Period
    1.53
    period
    1.51
    Activations Density 0.094%

    No Known Activations