© 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. 0-RES-JB
    11. 2075
    Prev
    Next
    INDEX
    Explanations

    medical and health-related information and advice

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    61
    +0.09
    0.3%
    1604
    +0.08
    0.3%
    75
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.09
    0.03
    514
    +0.08
    0.03
    64
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.06
    mergeFrom
    -0.69
    ArgumentParser
    -0.66
    ///**
    -0.61
    IActionResult
    -0.59
     "..\..\..\
    -0.59
    CreateIndex
    -0.59
    rália
    -0.59
    glPushMatrix
    -0.58
    FormBorderStyle
    -0.58
    POSITIVE LOGITS
     wise
    2.24
    wise
    2.15
     Wise
    1.94
    Wise
    1.91
     WISE
    1.78
    WISE
    1.73
     wisest
    1.38
     wiser
    1.24
     maneu
    1.19
     ibiza
    1.16
    Activations Density 0.096%

    No Known Activations