© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6003
    Prev
    Next
    INDEX
    Explanations

    advice or best practices related to software plugins or updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.07
    0.2%
    630
    +0.07
    0.2%
    1245
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.07
    0.05
    640
    +0.07
    0.04
    1650
    +0.07
    0.03
    Negative Logits
     affor
    -0.97
     unwarran
    -0.95
     inconce
    -0.94
     excru
    -0.93
     suscep
    -0.92
     shenan
    -0.92
     snoopy
    -0.92
     disagre
    -0.91
     impra
    -0.91
     inappro
    -0.90
    POSITIVE LOGITS
     those
    0.94
     ones
    0.88
    those
    0.87
    queles
    0.83
     những
    0.81
     olyan
    0.81
    那些
    0.75
     aquellos
    0.73
    Those
    0.73
     THOSE
    0.72
    Activations Density 0.486%

    No Known Activations