© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2809
    Prev
    Next
    INDEX
    Explanations

    locations, specifically town or city names

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1919
    +0.08
    0.2%
    1178
    +0.08
    0.2%
    1311
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    184
    +0.08
    0.02
    1120
    +0.07
    0.04
    Negative Logits
     Dale
    -0.86
    Dale
    -0.65
    []=$
    -0.61
    PathParam
    -0.59
    xFFFFFF
    -0.57
    DialogContent
    -0.55
    (@"%@",
    -0.52
    Và
    -0.52
    \}_{
    -0.51
     equality
    -0.51
    POSITIVE LOGITS
    dale
    1.80
    DALE
    1.13
     scrat
    1.09
     inext
    0.99
     maneu
    0.98
     deleter
    0.97
     unden
    0.95
     milo
    0.94
     Chá
    0.93
     unil
    0.92
    Activations Density 0.274%

    No Known Activations