© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    dates and durations

    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
    411
    +0.12
    0.4%
    303
    +0.11
    0.3%
    194
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.03
    1062
    +0.11
    0.05
    446
    +0.10
    0.04
    Negative Logits
     kras
    -0.74
     necesar
    -0.70
     paff
    -0.64
     tyn
    -0.63
     stihl
    -0.63
     ufe
    -0.62
     elek
    -0.61
     soe
    -0.61
     thut
    -0.60
     ert
    -0.60
    POSITIVE LOGITS
    3
    0.67
    prnewswire
    0.57
    three
    0.57
     Three
    0.56
     three
    0.53
    Three
    0.52
    imura
    0.48
     तीन
    0.48
    三
    0.48
     üç
    0.48
    Activations Density 0.303%

    No Known Activations