© 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. 4175
    Prev
    Next
    INDEX
    Explanations

    terms related to creation or implementation, especially in the context of reports, strategies, and functional technologies

    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
    1870
    +0.17
    0.8%
    2011
    +0.12
    0.5%
    528
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.06
    1183
    +0.12
    0.06
    1778
    +0.09
    0.07
    Negative Logits
    <bos>
    -3.11
     épreuve
    -0.69
     rubrique
    -0.69
     récolte
    -0.68
     récompense
    -0.67
     conférence
    -0.65
     leçon
    -0.65
     poursuite
    -0.62
     synchronize
    -0.61
     requête
    -0.60
    POSITIVE LOGITS
     bandung
    1.03
     stockholm
    1.03
     thut
    0.98
     Czechos
    0.97
     jaya
    0.95
     silikon
    0.94
     Minang
    0.93
     ftu
    0.90
     seoul
    0.89
     frankfurt
    0.88
    Activations Density 1.347%

    No Known Activations