© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    references to biblical characters and events

    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
    528
    +0.12
    0.3%
    31
    +0.08
    0.2%
    341
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.12
    0.02
    1120
    +0.08
    0.06
    1363
    +0.08
    0.05
    Negative Logits
     المكتبه
    -0.68
    gie
    -0.66
     etti
    -0.63
    document
    -0.63
     "@
    -0.63
     مست
    -0.63
     document
    -0.61
     mental
    -0.61
     las
    -0.60
     go
    -0.60
    POSITIVE LOGITS
     madonna
    2.13
     reluct
    2.00
     milf
    1.98
     thut
    1.97
     snoopy
    1.96
     fta
    1.95
     stockholm
    1.93
     nece
    1.91
     desir
    1.90
     volunte
    1.88
    Activations Density 0.391%

    No Known Activations