© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    words related to tricks or techniques

    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
    68
    +0.09
    0.3%
    122
    +0.07
    0.2%
    1482
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    901
    +0.09
    0.03
    1603
    +0.07
    0.02
    786
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.34
    ⓧ
    -0.70
    /***
    -0.68
    Globalization
    -0.64
    
    -0.63
    displayquote
    -0.57
    sec
    -0.56
    public
    -0.55
     declare
    -0.52
    deinit
    -0.52
    POSITIVE LOGITS
     trick
    2.84
    trick
    2.42
     Trick
    2.41
     tricks
    2.40
    Trick
    2.23
     Tricks
    2.11
    tricks
    2.11
     tricked
    1.27
     pixabay
    1.21
     shutterstock
    1.17
    Activations Density 0.175%

    No Known Activations