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. 10-RES-JB
    6. 1258
    Prev
    Next
    INDEX
    Explanations

    U.S. state abbreviations or references to states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.5%
    227
    +0.11
    0.4%
    1510
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1957
    +0.15
    0.04
    1593
    +0.11
    0.04
    227
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.79
    ⓧ
    -0.89
     springfox
    -0.79
    /***
    
    -0.76
    ///**
    -0.66
    /**
    -0.63
     trattano
    -0.62
    Портали
    -0.62
    /*
    -0.61
     bezeichneter
    -0.61
    POSITIVE LOGITS
     silikon
    1.07
     karton
    0.96
     akut
    0.94
     kaos
    0.93
     Keny
    0.92
     optik
    0.92
     juventus
    0.91
     mikrofon
    0.91
     antik
    0.91
     alkoh
    0.89
    Activations Density 0.104%

    No Known Activations