© 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. 1866
    Prev
    Next
    INDEX
    Explanations

    years represented by a four-digit number

    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
    +0.15
    0.8%
    1978
    +0.10
    0.5%
    382
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.15
    0.07
    1978
    +0.10
    0.07
    1614
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.45
    /**
    -1.04
    ⓧ
    -1.02
    
    -0.90
    <?
    -0.86
    /*
    -0.80
    <?
    -0.79
    #
    -0.78
     continue
    -0.75
     engage
    -0.69
    POSITIVE LOGITS
     Juf
    1.78
     maneu
    1.72
     increa
    1.69
     ftu
    1.68
     lele
    1.68
     affor
    1.66
     stockholm
    1.65
     accla
    1.58
     maroc
    1.56
     thut
    1.56
    Activations Density 0.156%

    No Known Activations