© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and technical aspects of Earth's features

    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
    1870
    +0.12
    0.3%
    678
    +0.10
    0.3%
    484
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.12
    0.04
    484
    +0.10
    0.03
    678
    +0.10
    0.06
    Negative Logits
     pegasus
    -0.60
     snoopy
    -0.58
     cushi
    -0.57
     fireman
    -0.56
     cocker
    -0.56
     wanderer
    -0.55
     ravens
    -0.54
     wolverine
    -0.54
     spiderman
    -0.54
     motherfucker
    -0.54
    POSITIVE LOGITS
     apparti
    0.78
     veda
    0.77
     lemp
    0.77
     Departement
    0.76
     jawa
    0.75
     Banjar
    0.75
     sement
    0.73
     Bekasi
    0.73
     portait
    0.70
     ouvre
    0.69
    Activations Density 0.491%

    No Known Activations