Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 787
    Prev
    Next
    INDEX
    Explanations

    references to evidence and events related to specific populations and controversies

    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
    +0.19
    0.7%
    1870
    +0.12
    0.4%
    581
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.19
    0.04
    424
    +0.12
    0.03
    1474
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.59
    ⓧ
    -0.76
     esternos
    -0.65
    ///**
    -0.65
     endwhile
    -0.63
    /***
    
    -0.63
     springfox
    -0.62
    Vegeu
    -0.61
     &___
    -0.60
    //}
    
    -0.58
    POSITIVE LOGITS
     stockholm
    1.08
     Minang
    1.07
     Jambi
    1.05
     quran
    1.02
     Juf
    1.02
     Bekasi
    1.02
     leonardo
    1.01
     aen
    0.99
     Palembang
    0.98
     hcm
    0.98
    Activations Density 0.803%

    No Known Activations