© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    words related to in-depth analysis and intense discussions

    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
    1535
    +0.20
    0.9%
    678
    +0.12
    0.5%
    1870
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.20
    0.14
    1535
    +0.12
    0.05
    1577
    +0.12
    0.14
    Negative Logits
    <bos>
    -3.35
    <?
    -0.79
    /**
    -0.72
    createNewFile
    -0.70
    IsRequired
    -0.70
    ⓧ
    -0.70
    .
    -0.69
    
    -0.67
     become
    -0.66
     continue
    -0.66
    POSITIVE LOGITS
     tramont
    1.72
     sappi
    1.71
     soggior
    1.59
     shopee
    1.55
     bayern
    1.55
     socie
    1.53
     ristor
    1.53
    !!</
    1.50
     applau
    1.50
     mosso
    1.50
    Activations Density 2.479%

    No Known Activations