© 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. 6384
    Prev
    Next
    INDEX
    Explanations

    references to social, political, and economic ideologies and concepts

    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
    1870
    +0.20
    0.6%
    1385
    +0.11
    0.3%
    678
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.04
    651
    +0.11
    0.03
    443
    +0.11
    0.06
    Negative Logits
     gaily
    -1.06
     reluct
    -1.04
     apprehen
    -0.98
     maneu
    -0.93
     shenan
    -0.93
     disagre
    -0.91
     pooh
    -0.91
     ineffec
    -0.91
     unspeak
    -0.91
     berea
    -0.85
    POSITIVE LOGITS
     sement
    0.86
     competen
    0.83
     palio
    0.82
     parati
    0.81
     exé
    0.80
     meras
    0.80
     poliester
    0.79
     poros
    0.78
     granada
    0.77
     katun
    0.77
    Activations Density 0.459%

    No Known Activations