© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    numbers and lists in a document

    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
    196
    +0.10
    0.3%
    674
    +0.10
    0.3%
    1387
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.10
    0.03
    1023
    +0.10
    0.03
    1183
    +0.10
    0.03
    Negative Logits
    Tecnologia
    -0.51
    COMPR
    -0.47
    melhor
    -0.47
    QtGui
    -0.46
    !("{
    -0.45
    HttpPut
    -0.45
    chuckles
    -0.45
    Calidad
    -0.45
    Abbiamo
    -0.44
    Acab
    -0.43
    POSITIVE LOGITS
     AMONG
    1.03
     among
    0.92
    among
    0.89
     Among
    0.88
     intersper
    0.88
     Amongst
    0.88
     tremb
    0.87
    Among
    0.83
     yong
    0.80
     amongst
    0.79
    Activations Density 0.059%

    No Known Activations