© 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. 172
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "other"

    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
    +0.15
    0.8%
    1984
    +0.07
    0.4%
    1265
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1910
    +0.15
    0.08
    1984
    +0.07
    0.08
    1504
    +0.06
    0.07
    Negative Logits
    <bos>
    -2.35
    
    -0.95
    /*
    -0.90
    <?
    -0.88
    ⓧ
    -0.87
    /**
    -0.84
    /***
    -0.82
    lateinit
    -0.77
    #
    -0.73
    ɵɵ
    -0.72
    POSITIVE LOGITS
     affor
    2.20
     maneu
    2.19
     accla
    2.00
     impra
    1.98
     increa
    1.96
     disagre
    1.91
     Intere
    1.91
     scrat
    1.90
     ibiza
    1.88
     excru
    1.87
    Activations Density 0.163%

    No Known Activations