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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5213
    Prev
    Next
    INDEX
    Explanations

    names and titles, particularly ones with suffixes like Jr., Sr., and Blvd

    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
    1896
    +0.15
    0.7%
    1265
    +0.15
    0.7%
    663
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.15
    0.04
    1110
    +0.15
    0.03
    663
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.71
     zima
    -0.85
     nmax
    -0.85
     fup
    -0.82
     guma
    -0.78
     esat
    -0.78
     umo
    -0.77
     fta
    -0.74
     thut
    -0.73
     jeste
    -0.71
    POSITIVE LOGITS
     bapt
    0.91
     Eqs
    0.86
     quoique
    0.84
     Présentation
    0.84
     soixante
    0.84
     considér
    0.84
     Équipe
    0.83
     partant
    0.82
     fidu
    0.81
     eqn
    0.81
    Activations Density 0.255%

    No Known Activations