© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12507
    Prev
    Next
    INDEX
    Explanations

    words related to programming and software development

    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
    2019
    +0.20
    0.7%
    736
    +0.13
    0.4%
    381
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.20
    0.06
    1265
    +0.13
    0.05
    736
    +0.13
    0.06
    Negative Logits
     himo
    -0.61
     bezeichneter
    -0.59
    watercolor
    -0.56
     OnTrigger
    -0.56
    htbp
    -0.52
    Välislingid
    -0.52
     Ceinture
    -0.51
    testify
    -0.50
    sneakers
    -0.50
    setupUi
    -0.50
    POSITIVE LOGITS
     inev
    0.93
     maneu
    0.93
     dises
    0.87
     encomp
    0.85
     stihl
    0.82
     tremb
    0.82
     sovere
    0.81
     excru
    0.81
     guarante
    0.80
     nece
    0.80
    Activations Density 0.140%

    No Known Activations