© 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 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. 11226
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical data or specifications

    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
    1741
    +0.16
    0.5%
    1757
    +0.12
    0.4%
    382
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.07
    1265
    +0.12
    0.05
    1961
    +0.12
    0.05
    Negative Logits
     kaos
    -0.79
     taba
    -0.75
    ."));
    -0.75
     optik
    -0.75
     antik
    -0.73
     panik
    -0.72
     balon
    -0.72
     boks
    -0.70
     maske
    -0.69
    ...");
    -0.68
    POSITIVE LOGITS
    Autoritní
    0.54
    Solución
    0.50
    OOTDTY
    0.48
     Suivez
    0.48
    Vanjske
    0.47
    djang
    0.45
    Lma
    0.45
     nessuna
    0.45
    Secara
    0.44
    Noice
    0.44
    Activations Density 0.428%

    No Known Activations