© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    references to monetary values or pricing information

    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
    1045
    +0.12
    0.4%
    161
    +0.11
    0.4%
    313
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.04
    1735
    +0.11
    0.02
    1805
    +0.10
    0.03
    Negative Logits
     kalo
    -0.68
     jawa
    -0.64
     Uang
    -0.64
     sih
    -0.64
     pedas
    -0.62
    borderTop
    -0.59
    qian
    -0.58
    qiang
    -0.58
    qiao
    -0.58
     madu
    -0.56
    POSITIVE LOGITS
     RM
    1.88
     Malaysian
    1.70
    RM
    1.69
     Malaysia
    1.61
    Malaysia
    1.61
     malaysia
    1.60
     malay
    1.44
    Malay
    1.39
     Rm
    1.38
     rm
    1.35
    Activations Density 0.294%

    No Known Activations