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. 913
    Prev
    Next
    INDEX
    Explanations

    geographical locations and historical events or contexts

    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
    +0.17
    0.6%
    1351
    +0.09
    0.3%
    11
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.17
    0.05
    1332
    +0.09
    0.06
    776
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.92
    /***
    
    -0.97
    ⓧ
    -0.78
    ///**
    -0.73
    <>
    
    -0.71
    /*++
    -0.68
    <?
    
    -0.65
    /*@
    -0.65
     defray
    -0.62
    Fuckin
    -0.61
    POSITIVE LOGITS
     lele
    0.99
     kram
    0.96
     kona
    0.94
     tucson
    0.91
     maksi
    0.89
     beverly
    0.88
     Minang
    0.87
     karton
    0.87
     budapest
    0.86
     kane
    0.85
    Activations Density 0.810%

    No Known Activations