© 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. 2577
    Prev
    Next
    INDEX
    Explanations

    countries or nationalities

    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
    605
    +0.10
    0.4%
    667
    +0.07
    0.3%
    50
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.10
    0.07
    683
    +0.07
    0.06
    1120
    +0.07
    0.06
    Negative Logits
    <bos>
    -1.08
    //
    -1.01
    ,
    -1.00
     continue
    -0.99
    .
    -0.99
     put
    -0.98
    /**
    -0.98
     don
    -0.96
     may
    -0.96
    public
    -0.94
    POSITIVE LOGITS
     increa
    3.68
     affor
    3.46
     guarante
    3.36
     maneu
    3.31
     depic
    3.31
     inev
    3.25
     reluct
    3.23
     disagre
    3.22
     strick
    3.21
     Juf
    3.21
    Activations Density 0.218%

    No Known Activations