© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1508
    Prev
    Next
    INDEX
    Explanations

    keywords related to certifications, training programs, and qualifications

    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
    220
    +0.18
    0.9%
    1757
    +0.15
    0.8%
    313
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.18
    0.03
    783
    +0.15
    0.03
    1044
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.85
     springfox
    -0.83
    ⓧ
    -0.79
    principalColumn
    -0.75
     onBackPressed
    -0.64
    /**
    -0.63
    ijuana
    -0.63
    /*
    -0.63
    expandindo
    -0.61
    WriteAttribute
    -0.61
    POSITIVE LOGITS
     certificate
    1.30
     Certificate
    1.16
     certificates
    1.14
    certificate
    1.11
    Certificate
    1.08
    Certificates
    1.01
     Certificates
    1.01
    certificates
    0.93
     CERTIFICATE
    0.90
     Jambi
    0.87
    Activations Density 0.349%

    No Known Activations