© 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. 6-RES-JB
    11. 2201
    Prev
    Next
    INDEX
    Explanations

    phrases relating to community engagement, environmental sustainability, and target demographics

    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
    +0.28
    1.1%
    168
    +0.09
    0.3%
    1363
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.28
    0.11
    962
    +0.09
    0.08
    1265
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.66
    ⓧ
    -0.88
    
    -0.83
    <?
    -0.82
    /**
    -0.75
    /***
    -0.66
    SOUNDBITE
    -0.65
    <?
    -0.62
    tagHelperRunner
    -0.61
    /*
    -0.59
    POSITIVE LOGITS
     lamborghini
    1.25
     chrysler
    1.17
     riviera
    1.14
     impra
    1.14
     accla
    1.14
     cabrio
    1.11
     isuzu
    1.11
     ibiza
    1.11
     ecru
    1.11
     outlander
    1.10
    Activations Density 2.268%

    No Known Activations