© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and calculations

    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
    1978
    +0.22
    0.8%
    382
    +0.15
    0.6%
    1515
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.22
    0.07
    1515
    +0.15
    0.05
    1187
    +0.13
    0.04
    Negative Logits
    Autoritní
    -0.75
     smtplib
    -0.73
     glaubte
    -0.67
     Pekan
    -0.67
    ffilm
    -0.66
     Embaj
    -0.60
    Mə
    -0.60
    もしろ
    -0.59
    Manbalar
    -0.58
    הע
    -0.57
    POSITIVE LOGITS
    1
    0.97
    0
    0.75
    2
    0.70
     ¹
    0.67
    3
    0.62
    5
    0.61
     Methanol
    0.60
    4
    0.60
    6
    0.59
    9
    0.59
    Activations Density 0.229%

    No Known Activations