© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    phrases related to website changes or product guarantees

    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
    +0.27
    1.7%
    478
    +0.14
    0.9%
    32
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    920
    +0.27
    0.07
    32
    +0.14
    0.07
    390
    +0.13
    0.06
    Negative Logits
    <bos>
    -3.57
     مرئيه
    -0.70
    setClass
    -0.69
    ,
    -0.67
    <?
    -0.66
     for
    -0.65
     AssemblyCompany
    -0.65
    है
    -0.64
    HasColumnType
    -0.64
     or
    -0.64
    POSITIVE LOGITS
     increa
    1.98
     reluct
    1.96
     accla
    1.96
     affor
    1.91
     Juf
    1.90
     inev
    1.90
     depic
    1.86
     disagre
    1.86
     maneu
    1.86
     emphat
    1.85
    Activations Density 0.151%

    No Known Activations