© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    news articles or stories published by specific outlets

    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
    1187
    +0.07
    0.2%
    1516
    +0.07
    0.2%
    397
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1584
    +0.07
    0.03
    11
    +0.07
    0.03
    1516
    +0.07
    0.03
    Negative Logits
    ⓧ
    -0.71
    
    -0.67
    насе
    -0.62
    نسية
    -0.62
    <bos>
    -0.61
     absorb
    -0.59
     promote
    -0.58
     poll
    -0.58
     reap
    -0.57
     assimilate
    -0.57
    POSITIVE LOGITS
    Story
    2.20
     Story
    1.94
    STORY
    1.49
     „,
    1.36
     STORY
    1.35
     §.
    1.33
     Vn
    1.30
     Secrétaire
    1.29
    story
    1.28
     hcm
    1.23
    Activations Density 0.197%

    No Known Activations