© 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. 6-RES-JB
    11. 8795
    Prev
    Next
    INDEX
    Explanations

    references to a person and their thoughts and actions, potentially related to conflict or planning

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.6%
    906
    +0.13
    0.6%
    604
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.14
    0.01
    1511
    +0.13
    0.02
    2015
    +0.11
    0.00
    Negative Logits
    <bos>
    -2.64
     kask
    -1.00
     embra
    -0.99
     makro
    -0.99
     robus
    -0.97
     permu
    -0.95
     traktor
    -0.95
     gend
    -0.92
    /***
    -0.91
     intersper
    -0.89
    POSITIVE LOGITS
    =""/>
    0.60
     scă
    0.57
    pozorn
    0.57
     ameste
    0.57
    []=$
    0.53
    isinstance
    0.53
     destinada
    0.53
     mwenye
    0.52
    />";
    0.52
    ValueError
    0.52
    Activations Density 1.047%

    No Known Activations