© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Carl" at various intensities

    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
    1961
    +0.11
    0.4%
    1323
    +0.10
    0.3%
    382
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.07
    1120
    +0.10
    0.06
    690
    +0.09
    0.06
    Negative Logits
    بو
    -0.69
     might
    -0.68
     prosecute
    -0.68
    ما
    -0.68
     gather
    -0.68
    s
    -0.67
    /*
    -0.67
     nadzie
    -0.66
     Сара
    -0.65
     приго
    -0.65
    POSITIVE LOGITS
     quoique
    1.64
     véhic
    1.60
     délib
    1.49
     honn
    1.46
     énon
    1.45
     soulign
    1.45
     ausp
    1.45
     accla
    1.45
     confé
    1.42
     Hez
    1.41
    Activations Density 0.514%

    No Known Activations