© 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. 6480
    Prev
    Next
    INDEX
    Explanations

    websites, URLs, or links

    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
    1343
    +0.17
    0.5%
    227
    +0.16
    0.5%
    2019
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    562
    +0.17
    0.03
    1619
    +0.16
    0.03
    1840
    +0.15
    0.02
    Negative Logits
     cytoplas
    -0.88
     Amiens
    -0.79
     Pyrene
    -0.79
     sceptre
    -0.77
     tolerably
    -0.75
     friable
    -0.74
     nephe
    -0.72
     frow
    -0.72
     insensible
    -0.70
     chert
    -0.69
    POSITIVE LOGITS
    com
    0.70
    net
    0.60
    org
    0.60
    Uwagi
    0.54
    html
    0.53
    info
    0.51
    NET
    0.50
    cn
    0.49
    Linki
    0.49
    COM
    0.49
    Activations Density 0.078%

    No Known Activations