© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3499
    Prev
    Next
    INDEX
    Explanations

    references to specific historical gates or locations, especially ones related to the term "Rajomon."

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1406
    +0.16
    0.8%
    1472
    +0.16
    0.8%
    1837
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1406
    +0.16
    0.04
    144
    +0.16
    0.04
    1343
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.24
     zima
    -0.77
    ⓧ
    -0.77
    /*
    -0.71
    
    -0.70
    <?
    -0.69
     usta
    -0.68
    /**
    -0.68
     moze
    -0.68
     jeste
    -0.68
    POSITIVE LOGITS
    aj
    0.85
     Aj
    0.84
     AJ
    0.83
     Laj
    0.79
     Raj
    0.79
     Baj
    0.78
     Paj
    0.77
    AJ
    0.77
    Aj
    0.76
    Raj
    0.75
    Activations Density 0.279%

    No Known Activations