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. 6034
    Prev
    Next
    INDEX
    Explanations

    surnames

    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
    +0.15
    1.0%
    874
    +0.11
    0.7%
    1035
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.15
    0.03
    1035
    +0.11
    0.03
    68
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.96
    
    
    -1.05
    ⓧ
    -0.98
    <?
    -0.98
    <?
    
    -0.81
    /**
    -0.81
    /*
    -0.74
    /***
    
    -0.71
    żdy
    -0.69
     rehabilitate
    -0.69
    POSITIVE LOGITS
     Smith
    1.53
    Smith
    1.47
     smith
    1.28
     SMITH
    1.28
    SMITH
    1.26
     Smiths
    1.21
    smith
    1.13
     thuy
    0.99
     Bulgar
    0.90
     Sén
    0.88
    Activations Density 0.098%

    No Known Activations