© 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. 2897
    Prev
    Next
    INDEX
    Explanations

    terms related to chemistry and biochemistry

    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
    325
    +0.10
    0.3%
    555
    +0.09
    0.3%
    331
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    928
    +0.10
    0.02
    155
    +0.09
    0.02
    184
    +0.07
    0.01
    Negative Logits
    DOCTYPE
    -0.61
     Bill
    -0.58
    struct
    -0.58
    судар
    -0.57
     directly
    -0.57
     won
    -0.57
    ტერ
    -0.57
    export
    -0.57
     serve
    -0.56
    cdn
    -0.56
    POSITIVE LOGITS
     chemistry
    2.27
     Chemistry
    2.10
    Chemistry
    1.84
     CHEMISTRY
    1.76
    chemistry
    1.68
     chemist
    1.61
     Chemist
    1.51
     squa
    1.49
     maneu
    1.46
     wien
    1.41
    Activations Density 0.233%

    No Known Activations