© 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 EvalsExportsinterp-engineNEWAPI 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. 15166
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to technology or software usage

    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
    381
    +0.11
    0.3%
    876
    +0.10
    0.3%
    453
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.11
    0.04
    1275
    +0.10
    0.04
    1415
    +0.09
    0.03
    Negative Logits
     Michoacán
    -0.73
     Áng
    -0.65
     Meksi
    -0.64
     Almería
    -0.64
     Cádiz
    -0.64
     silikon
    -0.62
     ekos
    -0.59
     maksi
    -0.57
     Guanajuato
    -0.56
     Lajos
    -0.55
    POSITIVE LOGITS
     impra
    0.92
     embodi
    0.80
     purcha
    0.78
     squa
    0.76
     coö
    0.74
     increa
    0.73
     seiz
    0.72
     scrat
    0.70
     resear
    0.70
     strick
    0.70
    Activations Density 0.222%

    No Known Activations