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. 9105
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or regulations related to licensing and permissions

    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
    +0.20
    0.9%
    1842
    +0.17
    0.7%
    394
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.20
    0.19
    1150
    +0.17
    0.05
    2019
    +0.11
    0.14
    Negative Logits
    <bos>
    -2.63
    /***
    
    -0.72
     springfox
    -0.66
    public
    -0.63
    //---
    -0.62
     AssemblyCompany
    -0.58
    ագրություններ
    -0.57
    protected
    -0.57
    ⓧ
    -0.57
    //--
    -0.56
    POSITIVE LOGITS
     maneu
    1.35
     unspeak
    1.27
     vété
    1.27
     impra
    1.25
     shenan
    1.23
     reluct
    1.21
     jurassic
    1.19
     sophistic
    1.19
     indescri
    1.17
     eiffel
    1.17
    Activations Density 6.200%

    No Known Activations