© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Pierce" in different contexts

    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
    889
    +0.10
    0.3%
    2004
    +0.09
    0.3%
    1068
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.06
    690
    +0.09
    0.06
    1363
    +0.09
    0.04
    Negative Logits
    <bos>
    -0.92
     تد
    -0.72
    tail
    -0.70
    માં
    -0.70
        
    -0.70
    вгения
    -0.69
    box
    -0.69
     ball
    -0.67
    /*
    -0.67
     зави
    -0.67
    POSITIVE LOGITS
     peppa
    2.39
     swarovski
    2.37
     desir
    2.30
     wien
    2.30
     squa
    2.29
     hairc
    2.27
     embra
    2.21
     aen
    2.20
     milf
    2.20
     stockholm
    2.19
    Activations Density 0.366%

    No Known Activations