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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 185
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.8%
    764
    +0.09
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    838
    +0.24
    0.04
    764
    +0.09
    0.03
    304
    +0.09
    0.00
    Negative Logits
    <bos>
    -1.86
    /***
    
    -1.03
    ///**
    -0.69
    aarrggbb
    -0.67
    <?
    
    -0.65
     betweenstory
    -0.65
    /**
    -0.65
     المعيارى
    -0.65
    onViewCreated
    -0.64
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
     Cuer
    0.82
     Darío
    0.74
     Municip
    0.73
     Haci
    0.72
     Contribu
    0.72
     Portugu
    0.72
     Più
    0.72
     jorge
    0.71
     Áng
    0.70
     alberto
    0.70
    Activations Density 0.234%

    No Known Activations