© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1046
    Prev
    Next
    INDEX
    Explanations

    references to and mentions of cell phones

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.07
    0.2%
    33
    +0.07
    0.2%
    422
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.07
    0.03
    1891
    +0.07
    0.03
    33
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.91
    ittoria
    -0.83
    <?
    -0.78
    /**
    -0.71
     dras
    -0.64
    /***
    -0.64
     solidar
    -0.62
    /*++
    -0.62
    engeance
    -0.58
    énus
    -0.58
    POSITIVE LOGITS
     tucson
    0.97
     bandung
    0.94
     Minang
    0.91
     mondeo
    0.90
     hilux
    0.87
     susun
    0.87
     vectra
    0.85
     isuzu
    0.85
     Hitam
    0.84
     jetta
    0.83
    Activations Density 0.188%

    No Known Activations