© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    locations such as cities and buildings

    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
    1744
    +0.08
    0.2%
    1262
    +0.07
    0.2%
    474
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.03
    1927
    +0.07
    0.06
    184
    +0.07
    0.03
    Negative Logits
    stddef
    -0.62
     Rasmus
    -0.54
     demo
    -0.51
     Larissa
    -0.51
    Xna
    -0.49
     di
    -0.49
     Adamson
    -0.48
    lop
    -0.47
     MTS
    -0.47
     Wur
    -0.47
    POSITIVE LOGITS
     susun
    0.90
     stik
    0.89
    zegor
    0.89
     seksi
    0.87
     tanong
    0.85
     fei
    0.82
     andes
    0.82
     mahd
    0.82
     ananas
    0.81
     kaos
    0.81
    Activations Density 0.350%

    No Known Activations