© 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. 1210
    Prev
    Next
    INDEX
    Explanations

    references to scheduled events or times in the British Summer Time (BST) timezone

    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
    1416
    +0.09
    0.2%
    1983
    +0.09
    0.2%
    893
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.05
    1120
    +0.09
    0.05
    283
    +0.09
    0.02
    Negative Logits
    않
    -0.62
     copper
    -0.59
     않는
    -0.55
     않았
    -0.52
    copper
    -0.52
    Copper
    -0.51
    Alcal
    -0.51
     Copper
    -0.50
    progressDialog
    -0.50
    ý
    -0.50
    POSITIVE LOGITS
     BST
    2.06
    BST
    1.38
     CEST
    1.16
     casio
    1.05
     roth
    1.05
     orlando
    1.02
     bst
    1.01
     bose
    0.99
     jbl
    0.97
     mcdonald
    0.97
    Activations Density 0.361%

    No Known Activations