© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    references to publications or articles

    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
    1145
    +0.08
    0.2%
    920
    +0.07
    0.2%
    1361
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.08
    0.03
    1341
    +0.07
    0.03
    427
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.02
    разви
    -0.77
     die
    -0.70
     register
    -0.69
     do
    -0.68
     apply
    -0.68
     online
    -0.68
     bring
    -0.67
     бер
    -0.67
     charge
    -0.67
    POSITIVE LOGITS
     stockholm
    2.07
     lidl
    2.06
     Page
    2.02
     wien
    2.00
     accla
    1.99
     eiffel
    1.99
     wikihow
    1.93
     ?...
    1.91
     emphat
    1.90
     franz
    1.90
    Activations Density 0.217%

    No Known Activations