© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    digits and financial terms

    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
    674
    +0.12
    0.3%
    453
    +0.12
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.12
    0.03
    1550
    +0.12
    0.01
    658
    +0.10
    0.03
    Negative Logits
     useCallback
    -0.60
    drawRect
    -0.48
    setObjectName
    -0.47
    rawQuery
    -0.46
     useParams
    -0.43
    flexDirection
    -0.43
    록
    -0.43
     performances
    -0.43
     아이콘
    -0.42
    −/−
    -0.42
    POSITIVE LOGITS
     dispen
    1.00
     fatis
    0.98
     socie
    0.97
     pessi
    0.95
     michelin
    0.94
     gsx
    0.93
     igno
    0.92
     affez
    0.90
     vespa
    0.90
     lamborghini
    0.90
    Activations Density 0.151%

    No Known Activations