© 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. 232
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Rebecca 9"

    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
    251
    +0.11
    0.4%
    687
    +0.10
    0.3%
    61
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.04
    1120
    +0.10
    0.04
    690
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.79
    
    -0.67
    ByVersion
    -0.63
    <?
    -0.61
    SequentialGroup
    -0.55
    ⓧ
    -0.55
    qiang
    -0.54
     onSave
    -0.53
    обеди
    -0.52
    énégal
    -0.52
    POSITIVE LOGITS
     Rebecca
    1.09
     véhic
    1.01
    Rebecca
    1.00
     kac
    0.97
     silikon
    0.94
     lele
    0.92
     jaya
    0.91
     affor
    0.91
     saba
    0.91
     aussitôt
    0.91
    Activations Density 0.284%

    No Known Activations