© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6714
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions and personal achievements

    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
    944
    +0.10
    0.3%
    1525
    +0.09
    0.3%
    961
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.10
    0.10
    1533
    +0.09
    0.02
    1126
    +0.09
    0.06
    Negative Logits
     amada
    -0.56
     masculina
    -0.55
     sagrada
    -0.55
    Flere
    -0.54
     estimés
    -0.54
    ždý
    -0.52
     חיצוניים
    -0.51
     casera
    -0.51
     noiva
    -0.51
     muchacha
    -0.50
    POSITIVE LOGITS
     accla
    0.97
     reluct
    0.94
     reconno
    0.88
     shes
    0.86
     intrigu
    0.86
     depic
    0.86
     strick
    0.84
     apprehen
    0.84
     lovel
    0.81
     Abbé
    0.81
    Activations Density 1.301%

    No Known Activations