© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 8591
    Prev
    Next
    INDEX
    Explanations

    uses word stems and suffixes found in educational contexts, especially in the field of science and academia

    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
    +0.17
    1.0%
    690
    +0.12
    0.7%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.17
    0.12
    1129
    +0.12
    0.12
    667
    +0.10
    0.09
    Negative Logits
    <bos>
    -3.30
    if
    -0.88
    else
    -0.86
    /**
    -0.85
    get
    -0.82
    go
    -0.81
     get
    -0.81
    AsUp
    -0.80
    HasIndex
    -0.80
    .
    -0.80
    POSITIVE LOGITS
     maneu
    2.78
     accla
    2.55
     increa
    2.52
     impra
    2.52
     stockholm
    2.51
     emphat
    2.48
     Juf
    2.44
     depic
    2.43
     strick
    2.41
     affor
    2.38
    Activations Density 1.974%

    No Known Activations