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. 6114
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about products

    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
    1387
    +0.16
    0.9%
    50
    +0.16
    0.9%
    596
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.16
    0.04
    596
    +0.16
    0.03
    568
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.66
    lateinit
    -0.69
    
    
    -0.66
    /**
    -0.62
    HasIndex
    -0.60
    ValueGenerated
    -0.60
    <?
    
    -0.60
    runApp
    -0.59
     collect
    -0.58
    <>
    
    -0.58
    POSITIVE LOGITS
     Juf
    1.35
     stockholm
    1.27
     ecru
    1.26
     sovere
    1.24
     embodi
    1.24
     coö
    1.20
     affez
    1.20
     nmax
    1.20
     Minang
    1.20
     waer
    1.19
    Activations Density 0.143%

    No Known Activations