© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    images, directories, and command lines in a technical context

    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
    227
    +0.12
    0.4%
    1317
    +0.11
    0.3%
    876
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.12
    0.03
    2010
    +0.11
    0.03
    227
    +0.11
    0.03
    Negative Logits
    Ekster
    -0.89
    Galería
    -0.88
    Requisitos
    -0.87
     <",
    -0.86
    Aplicación
    -0.85
    Algunas
    -0.85
    معلومات
    -0.84
    اقرأ
    -0.84
    Ilustra
    -0.84
    Apesar
    -0.84
    POSITIVE LOGITS
     ?...
    2.06
     contex
    2.01
     deleter
    1.99
     increa
    1.99
     secon
    1.98
     !...
    1.96
     squa
    1.96
     uniqu
    1.96
     effe
    1.95
     fto
    1.90
    Activations Density 0.074%

    No Known Activations