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. 6074
    Prev
    Next
    INDEX
    Explanations

    information related to publication details, copyright, and contact information for various materials

    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
    1506
    +0.14
    0.9%
    805
    +0.12
    0.7%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.14
    0.06
    1837
    +0.12
    0.05
    1527
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -1.18
    /**
    -0.99
    <?
    -0.88
    
    
    -0.86
    /***
    
    -0.71
     disbur
    -0.69
     circulate
    -0.61
     endow
    -0.59
     springfox
    -0.59
    POSITIVE LOGITS
     ananas
    0.96
     marte
    0.96
     bayern
    0.95
     optik
    0.93
     mikrofon
    0.92
     maroc
    0.91
     vasi
    0.90
     karton
    0.89
     lele
    0.88
     makro
    0.87
    Activations Density 0.136%

    No Known Activations