© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    phrases related to government departments or geographical locations

    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
    1387
    +0.14
    0.7%
    204
    +0.14
    0.7%
    1464
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.14
    0.04
    648
    +0.14
    0.04
    227
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.97
    <!--[
    -0.66
    setAdapter
    -0.65
    omitempty
    -0.61
    <?
    -0.61
    /***
    -0.59
    JoinTable
    -0.59
    setFill
    -0.59
    ttemberg
    -0.58
    četně
    -0.56
    POSITIVE LOGITS
     Kansas
    1.39
     KANSAS
    1.36
    Kansas
    1.35
     Kans
    1.24
     sergio
    1.03
     Juf
    1.02
     kc
    0.97
     madonna
    0.95
     impra
    0.94
     applau
    0.94
    Activations Density 0.343%

    No Known Activations