© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3462
    Prev
    Next
    INDEX
    Explanations

    specific body parts and medical terms related to physical therapy or health

    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
    2011
    +0.21
    1.2%
    528
    +0.18
    1.0%
    1961
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.21
    0.04
    1741
    +0.18
    0.00
    1097
    +0.15
    0.05
    Negative Logits
     Molto
    -0.92
     poetical
    -0.85
     Forse
    -0.80
     PHILOS
    -0.79
     sappi
    -0.78
     papà
    -0.78
     Mentre
    -0.77
     quegli
    -0.77
     Queste
    -0.76
    bardziej
    -0.76
    POSITIVE LOGITS
     Pel
    1.33
    Pel
    1.26
     pel
    0.99
     Mam
    0.93
    pel
    0.92
    Mam
    0.86
    PEL
    0.86
     pellet
    0.84
     schema
    0.82
     Schema
    0.81
    Activations Density 0.596%

    No Known Activations