© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    50
    +0.12
    0.6%
    650
    +0.05
    0.3%
    411
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.12
    0.06
    1356
    +0.05
    0.06
    116
    +0.05
    0.05
    Negative Logits
    <bos>
    -2.13
    ⓧ
    -0.89
    public
    -0.86
    })();
    -0.80
    //
    -0.79
    /**
    -0.78
    enumerate
    -0.76
    ,
    -0.76
     continue
    -0.76
    private
    -0.75
    POSITIVE LOGITS
     maneu
    2.50
     affor
    2.24
     increa
    2.17
     stockholm
    2.16
     accla
    2.13
     eiffel
    2.10
     reluct
    2.10
     impra
    2.08
     depic
    2.05
     scrat
    2.04
    Activations Density 0.077%

    No Known Activations