© 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. 12200
    Prev
    Next
    INDEX
    Explanations

    information related to coding and programming languages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    explanations or descriptions of processes in programming contexts.

    oai_token-act-pair · gpt-4oTriggered by @thinkspring96
    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
    +0.24
    0.8%
    856
    +0.15
    0.5%
    872
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.24
    -0.01
    872
    +0.15
    0.09
    1511
    +0.15
    0.01
    Negative Logits
     Singapur
    -0.73
     Demokrat
    -0.71
     Siria
    -0.69
     Milán
    -0.68
     Palestina
    -0.68
    Biografia
    -0.67
     Islas
    -0.67
    Artigo
    -0.67
    Televis
    -0.66
    Tecnologia
    -0.66
    POSITIVE LOGITS
     intermitt
    1.89
     maneu
    1.86
     increa
    1.84
     affor
    1.82
     impra
    1.81
     encomp
    1.78
     scrat
    1.76
     emphat
    1.72
     reluct
    1.72
     suscep
    1.70
    Activations Density 1.163%

    No Known Activations