© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or event, specifically related to "wick."

    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
    397
    +0.08
    0.2%
    1271
    +0.08
    0.2%
    32
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.05
    283
    +0.08
    0.01
    1120
    +0.07
    0.04
    Negative Logits
     răm
    -0.68
    Vlast
    -0.63
     arată
    -0.63
     își
    -0.60
     freilich
    -0.59
    asthan
    -0.56
     istot
    -0.55
     îi
    -0.54
     vrea
    -0.54
    Teraz
    -0.54
    POSITIVE LOGITS
     Displacement
    0.99
     meis
    0.97
     ù
    0.97
     sopr
    0.92
    !!</
    0.92
     peccato
    0.91
     Politica
    0.90
     Settembre
    0.89
     maroc
    0.89
     ananas
    0.88
    Activations Density 0.334%

    No Known Activations