© 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. 2363
    Prev
    Next
    INDEX
    Explanations

    references to religious stories and mythical figures with a critical perspective

    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
    +0.09
    0.4%
    1150
    +0.08
    0.4%
    1385
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.09
    0.30
    1870
    +0.08
    0.04
    1150
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.17
    /***
    -0.78
    ⓧ
    -0.74
    /**
    -0.73
    <?
    -0.69
    //---
    -0.67
     defray
    -0.64
     disbur
    -0.63
    public
    -0.63
    
    -0.62
    POSITIVE LOGITS
     Minang
    1.18
     bandung
    1.13
     sappi
    1.11
     jawa
    1.07
     Muhamma
    1.04
     haup
    1.03
     applau
    1.02
     Jambi
    1.00
     maroc
    0.99
     jaya
    0.98
    Activations Density 5.326%

    No Known Activations