© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or suggestions on a webpage

    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
    +0.25
    1.0%
    1150
    +0.07
    0.3%
    468
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.25
    0.10
    1786
    +0.07
    0.05
    383
    +0.06
    0.07
    Negative Logits
    <bos>
    -2.04
    HasColumnType
    -0.83
    /**
    -0.72
    IsRequired
    -0.72
    Alemania
    -0.71
    for
    -0.69
    enumerate
    -0.68
    /**
    -0.68
    package
    -0.68
    addComponent
    -0.68
    POSITIVE LOGITS
     maneu
    2.34
     affor
    2.21
     increa
    2.14
     guarante
    2.13
     secon
    2.09
     accla
    2.07
     ftu
    2.06
     unden
    2.05
     reluct
    2.05
     stockholm
    2.05
    Activations Density 1.185%

    No Known Activations