© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    institutional affiliations and professional titles

    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
    67
    +0.10
    0.3%
    553
    +0.09
    0.3%
    1363
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.05
    1343
    +0.09
    0.05
    690
    +0.09
    0.05
    Negative Logits
     dollari
    -0.74
     fatale
    -0.71
     giac
    -0.68
     provinciale
    -0.66
     plis
    -0.62
     yw
    -0.62
     ISTAT
    -0.61
     boxe
    -0.60
    Бахар
    -0.60
     dones
    -0.59
    POSITIVE LOGITS
     gaily
    1.37
     apprehen
    1.35
     unspeak
    1.33
     cushi
    1.32
     tolerably
    1.28
     hairc
    1.27
     affor
    1.25
     impra
    1.24
     ineffec
    1.21
     plenti
    1.18
    Activations Density 0.336%

    No Known Activations