© 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. 2683
    Prev
    Next
    INDEX
    Explanations

    information about events, locations, and contacts for community activities and announcements

    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
    1937
    +0.13
    0.4%
    1233
    +0.11
    0.4%
    553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.13
    0.03
    1120
    +0.11
    0.02
    553
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.66
    bondale
    -0.65
    memoized
    -0.64
    SequentialGroup
    -0.63
     чу
    -0.62
    XMLSchema
    -0.62
     Великой
    -0.60
    AccessorTable
    -0.58
    obox
    -0.58
    AFP
    -0.58
    POSITIVE LOGITS
     Hart
    2.94
    Hart
    2.46
     HART
    1.98
    HART
    1.68
     quoique
    1.65
     ftu
    1.61
     Chapitre
    1.61
     hart
    1.59
     fta
    1.58
     accla
    1.55
    Activations Density 0.194%

    No Known Activations