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. 2428
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal experiences and interactions in a therapeutic or supportive setting

    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
    2019
    +0.26
    1.4%
    50
    +0.21
    1.1%
    1535
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.26
    0.10
    1535
    +0.21
    0.06
    1445
    +0.17
    0.07
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -1.44
    /***
    
    -1.26
    /**
    -1.20
    
    
    -1.11
    ///**
    -1.00
    /*
    -0.94
    <?
    -0.92
     springfox
    -0.82
    /*!
    
    -0.78
    POSITIVE LOGITS
     marea
    0.69
     véhic
    0.66
     échou
    0.63
     soulign
    0.63
     cabina
    0.61
     nécess
    0.61
     épu
    0.60
     coû
    0.59
     résult
    0.59
     néanmoins
    0.59
    Activations Density 0.364%

    No Known Activations