© 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 EvalsExportsinterp-engineNEWAPI 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. 15162
    Prev
    Next
    INDEX
    Explanations

    references to time durations and frequencies

    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
    1105
    +0.10
    0.3%
    110
    +0.09
    0.3%
    1317
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1105
    +0.10
    0.05
    520
    +0.09
    0.03
    110
    +0.08
    0.04
    Negative Logits
    IActionResult
    -0.53
    Puis
    -0.53
    usercontent
    -0.52
    TextWatcher
    -0.51
    ViewInit
    -0.50
    citet
    -0.50
    SerializeField
    -0.48
     населення
    -0.47
     Wikimédia
    -0.47
     глазах
    -0.47
    POSITIVE LOGITS
     accla
    1.05
     excru
    1.03
     maneu
    1.02
     alre
    0.96
     strick
    0.96
     shenan
    0.95
     emphat
    0.95
     encomp
    0.95
     inev
    0.95
     invin
    0.94
    Activations Density 0.433%

    No Known Activations