© 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. 8362
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for names containing the string "Sag" followed by a single letter

    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
    812
    +0.27
    1.4%
    680
    +0.17
    0.9%
    169
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.27
    0.05
    227
    +0.17
    0.07
    1741
    +0.17
    0.00
    Negative Logits
     osal
    -0.82
     alip
    -0.82
     kule
    -0.81
     couverte
    -0.80
     intersper
    -0.79
     Incenti
    -0.79
     prouve
    -0.78
     kasa
    -0.78
     intégrée
    -0.78
     garantit
    -0.76
    POSITIVE LOGITS
     Sag
    0.80
    Sag
    0.75
     sag
    0.59
    tă
    0.57
    SAG
    0.55
    saga
    0.54
     MainAxisSize
    0.54
    ългар
    0.53
    ylase
    0.52
    isert
    0.52
    Activations Density 0.639%

    No Known Activations