© 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. 6352
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to software development

    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
    876
    +0.14
    0.4%
    453
    +0.13
    0.4%
    511
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.14
    0.00
    167
    +0.13
    0.02
    1284
    +0.09
    0.02
    Negative Logits
     seksi
    -0.62
     protokol
    -0.60
     bakteri
    -0.60
     Meksi
    -0.59
     kemer
    -0.56
     organik
    -0.56
     besi
    -0.56
     elektronik
    -0.56
     Öster
    -0.55
     taha
    -0.55
    POSITIVE LOGITS
     aspetta
    0.71
     dicono
    0.71
     manteau
    0.70
     velours
    0.69
     desideri
    0.68
     esempi
    0.67
     dichi
    0.67
     automne
    0.65
     intende
    0.64
     saluti
    0.64
    Activations Density 0.087%

    No Known Activations