© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or areas

    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
    874
    +0.12
    0.4%
    1141
    +0.09
    0.3%
    1565
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.12
    0.03
    564
    +0.09
    0.03
    603
    +0.09
    0.02
    Negative Logits
     Mónica
    -1.16
     Darío
    -1.03
     Mejía
    -0.94
    <bos>
    -0.94
     Belén
    -0.85
     Agustín
    -0.82
     Valentín
    -0.79
     Víctor
    -0.76
     Áng
    -0.75
     Rubén
    -0.74
    POSITIVE LOGITS
     Ca
    2.86
    Ca
    2.46
     ca
    1.95
     Calcium
    1.42
     calcium
    1.40
    Calcium
    1.35
    calcium
    1.20
     Capo
    0.93
     Cahill
    0.90
    ca
    0.90
    Activations Density 0.198%

    No Known Activations