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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7215
    Prev
    Next
    INDEX
    Explanations

    references to interior design elements and materials like colors, furniture, and lighting

    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
    50
    +0.28
    1.1%
    1385
    +0.17
    0.7%
    1013
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.28
    0.16
    1802
    +0.17
    0.07
    1780
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.60
    ⓧ
    -1.30
    /**
    -1.24
    
    -1.17
    <?
    -1.07
    /*
    -0.99
    <?
    -0.98
     intersper
    -0.87
     disbur
    -0.83
    /***
    -0.82
    POSITIVE LOGITS
     catég
    0.84
     marié
    0.69
     soulign
    0.64
     chrétien
    0.62
     Indah
    0.60
     télévis
    0.60
     Ikan
    0.59
     useRouter
    0.59
     curieux
    0.59
     devenus
    0.59
    Activations Density 1.782%

    No Known Activations