© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2645
    Prev
    Next
    INDEX
    Explanations

    numerical and financial terms, specifically related to corporate financial performance and projections

    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
    +0.10
    0.5%
    764
    +0.05
    0.2%
    734
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.10
    0.11
    491
    +0.05
    0.04
    680
    +0.05
    0.07
    Negative Logits
    <bos>
    -1.73
    
    -0.96
    <?
    -0.89
    /**
    -0.85
    /***
    -0.82
    <?
    -0.79
    ⓧ
    -0.79
     abolish
    -0.71
    public
    -0.68
     mobilize
    -0.68
    POSITIVE LOGITS
     lele
    1.52
     saar
    1.47
     bandung
    1.41
     meis
    1.39
     hcm
    1.34
     Minang
    1.33
     kram
    1.31
     gend
    1.30
     idr
    1.30
     wien
    1.30
    Activations Density 1.909%

    No Known Activations