Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6124
    Prev
    Next
    INDEX
    Explanations

    financial figures and technical details, possibly related to a specific industry or domain

    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
    555
    +0.20
    1.0%
    1624
    +0.14
    0.7%
    50
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.20
    0.02
    900
    +0.14
    0.04
    1343
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.97
    ///**
    -0.73
    <!--
    
    -0.64
    /***
    
    -0.63
    <?
    
    -0.63
     rehabilitate
    -0.63
     ratify
    -0.63
    //{
    
    -0.58
    /*!
    
    -0.57
    netinet
    -0.56
    POSITIVE LOGITS
     karton
    0.91
     silikon
    0.83
     optik
    0.80
     kristal
    0.78
     mentale
    0.77
    +
    0.74
     keramik
    0.73
     alkoh
    0.73
     Heeren
    0.71
     keram
    0.70
    Activations Density 0.229%

    No Known Activations