© 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. 0-RES-JB
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    words related to the spine, back pain, and associated medical conditions

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1805
    +0.10
    0.3%
    1909
    +0.08
    0.2%
    1023
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.02
    1805
    +0.08
    0.02
    690
    +0.08
    0.03
    Negative Logits
    <?
    -0.93
    ⓧ
    -0.89
     encomp
    -0.84
     depic
    -0.84
     contribue
    -0.82
     simplif
    -0.80
     inconce
    -0.80
     volunte
    -0.77
     Voilà
    -0.77
     Gorb
    -0.76
    POSITIVE LOGITS
     spine
    2.88
     Spine
    2.22
    spine
    2.15
     spinal
    2.07
     spines
    2.06
    Spine
    1.94
    spinal
    1.54
     Spinal
    1.42
     backbone
    1.39
     vertebrae
    1.25
    Activations Density 0.217%

    No Known Activations