© 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. 1799
    Prev
    Next
    INDEX
    Explanations

    mentions of medical centers related to training and certification

    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
    585
    +0.07
    0.2%
    1841
    +0.07
    0.2%
    1942
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.01
    1363
    +0.07
    0.02
    1343
    +0.07
    0.03
    Negative Logits
    invokeLater
    -0.84
    IGraphics
    -0.74
    PerformLayout
    -0.72
    WireFormat
    -0.71
    addComponent
    -0.71
    enterOuterAlt
    -0.71
    penup
    -0.69
    AutoScaleMode
    -0.68
    getClassLoader
    -0.68
    
    -0.68
    POSITIVE LOGITS
    tering
    2.16
     perfet
    2.05
     maneu
    2.05
     affor
    2.02
     disreg
    1.99
     increa
    1.99
     indestru
    1.98
     erad
    1.97
     scrat
    1.95
     suspic
    1.93
    Activations Density 0.241%

    No Known Activations