© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 641
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Porter."

    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
    1323
    +0.10
    0.3%
    1451
    +0.09
    0.3%
    1757
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.04
    1120
    +0.09
    0.03
    1343
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.78
     McLaugh
    -0.69
     McCulloch
    -0.67
     Mulligan
    -0.66
     Biggs
    -0.64
     Lindley
    -0.64
     intersper
    -0.63
     Bowden
    -0.60
     Hirst
    -0.60
    <?
    -0.58
    POSITIVE LOGITS
     Porter
    1.19
    Porter
    1.14
     saar
    0.98
     porter
    0.96
     tanong
    0.91
     Ottobre
    0.91
     sappi
    0.87
     miele
    0.83
     Luglio
    0.83
     berlina
    0.83
    Activations Density 0.248%

    No Known Activations