© 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. 12517
    Prev
    Next
    INDEX
    Explanations

    quotations and references from articles and publications

    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
    +0.27
    0.9%
    1535
    +0.22
    0.7%
    872
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.27
    0.09
    1535
    +0.22
    0.08
    1445
    +0.17
    0.08
    Negative Logits
     Darum
    -0.65
     Kto
    -0.64
     NKC
    -0.61
     Zwar
    -0.60
     BnF
    -0.59
     COMPOUNDS
    -0.57
     AVEC
    -0.57
     Compañía
    -0.57
     Ży
    -0.57
     Bekasi
    -0.56
    POSITIVE LOGITS
    This
    0.64
     indescri
    0.63
    Thus
    0.63
    jaja
    0.62
    rilis
    0.62
     intrigu
    0.61
     jacques
    0.59
     unspeak
    0.59
    hermoso
    0.59
     haba
    0.59
    Activations Density 0.337%

    No Known Activations