© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5029
    Prev
    Next
    INDEX
    Explanations

    phrases related to education, diversity, culture, and societal shifts

    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
    198
    +0.16
    0.4%
    80
    +0.08
    0.2%
    764
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.06
    1586
    +0.08
    0.04
    113
    +0.07
    0.03
    Negative Logits
     philanth
    -0.99
     shenan
    -0.95
     encomp
    -0.92
     impra
    -0.91
     volunte
    -0.90
     maneu
    -0.83
     accla
    -0.82
     pamph
    -0.81
     Jusqu
    -0.80
     McLaugh
    -0.80
    POSITIVE LOGITS
     increasingly
    0.74
    __(/*!
    0.63
    weile
    0.62
     Palabra
    0.57
    endphp
    0.55
    ChildScrollView
    0.55
    GEBURTSDATUM
    0.55
    లాలు
    0.55
     beginnetje
    0.55
     allt
    0.54
    Activations Density 0.689%

    No Known Activations