© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    details related to events or incidents as reported by various sources

    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
    +0.21
    0.8%
    2019
    +0.10
    0.4%
    381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.21
    0.09
    1445
    +0.10
    0.08
    2019
    +0.10
    0.07
    Negative Logits
    <bos>
    -1.54
     anse
    -0.88
     provence
    -0.86
     utop
    -0.84
     rè
    -0.82
     parf
    -0.81
     solidar
    -0.80
     bander
    -0.79
     notor
    -0.79
     handels
    -0.79
    POSITIVE LOGITS
     actionTypes
    0.83
     soulign
    0.83
     unspeak
    0.81
     réput
    0.79
     pymysql
    0.78
     tantôt
    0.73
     spécialement
    0.72
     exceptionnelle
    0.71
     destinées
    0.70
     dotenv
    0.70
    Activations Density 0.777%

    No Known Activations