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. 6071
    Prev
    Next
    INDEX
    Explanations

    details related to a product offering or a set of services with a focus on payment terms and benefits

    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
    +0.19
    0.8%
    1150
    +0.13
    0.6%
    2034
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.19
    0.14
    1438
    +0.13
    0.07
    1013
    +0.10
    0.15
    Negative Logits
    <bos>
    -2.73
    /***
    
    -0.75
    ///**
    -0.74
     springfox
    -0.73
    ⓧ
    -0.70
    glMatrixMode
    -0.67
    /*!
    
    -0.67
    Atsauces
    -0.66
    frastructure
    -0.65
    Fordítás
    -0.65
    POSITIVE LOGITS
     saar
    1.25
     maksi
    1.21
     kaos
    1.17
     seksi
    1.15
     maneu
    1.15
     kase
    1.12
     maske
    1.12
     uhr
    1.10
     idr
    1.09
     optik
    1.08
    Activations Density 3.265%

    No Known Activations