© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    locations, organizations, and events related to specific places or entities

    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
    690
    +0.10
    0.3%
    1120
    +0.09
    0.3%
    511
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.08
    690
    +0.09
    0.07
    1735
    +0.08
    0.05
    Negative Logits
    ,
    -1.37
     die
    -1.36
     so
    -1.35
     don
    -1.34
     can
    -1.33
    .
    -1.33
    !
    -1.33
     or
    -1.30
     of
    -1.30
     should
    -1.29
    POSITIVE LOGITS
     maneu
    5.01
     squa
    4.88
     emphat
    4.86
     stockholm
    4.82
     increa
    4.80
     accla
    4.69
     fuf
    4.67
     ftu
    4.62
     fta
    4.58
     strick
    4.58
    Activations Density 0.317%

    No Known Activations