© 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. 5906
    Prev
    Next
    INDEX
    Explanations

    mentions of certification or being certified

    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
    +0.16
    0.9%
    172
    +0.15
    0.9%
    555
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.16
    0.03
    1677
    +0.15
    0.02
    667
    +0.12
    0.02
    Negative Logits
    <bos>
    -3.31
    ⓧ
    -0.75
    setDo
    -0.67
    //---
    -0.63
    //----
    -0.63
    JspWriter
    -0.59
    Высота
    -0.59
    مصادر
    -0.59
    /*++
    -0.58
     arrange
    -0.57
    POSITIVE LOGITS
     bandung
    1.24
     Certifications
    1.21
     Minang
    1.19
     certification
    1.17
     jaya
    1.17
     increa
    1.16
     Certification
    1.16
     certifications
    1.15
     wien
    1.12
     roberto
    1.11
    Activations Density 0.063%

    No Known Activations