© 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. 1872
    Prev
    Next
    INDEX
    Explanations

    references to the University of Iowa and the University of Maryland

    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
    50
    +0.10
    0.5%
    687
    +0.05
    0.2%
    1639
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.10
    0.07
    525
    +0.05
    0.07
    240
    +0.04
    0.06
    Negative Logits
    public
    -0.97
    <bos>
    -0.94
     continue
    -0.90
    //
    -0.87
     also
    -0.87
     put
    -0.86
    /**
    -0.86
    /**
    -0.86
    ///
    -0.85
    hline
    -0.85
    POSITIVE LOGITS
     affor
    3.20
     maneu
    3.17
     increa
    3.15
     stockholm
    3.00
     impra
    2.98
     inev
    2.97
     accla
    2.95
     squa
    2.93
     fta
    2.90
     perfet
    2.88
    Activations Density 0.194%

    No Known Activations