© 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. 7410
    Prev
    Next
    INDEX
    Explanations

    phrases with quotation marks or special characters

    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
    2019
    +0.29
    1.1%
    304
    +0.16
    0.6%
    1438
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.29
    0.04
    736
    +0.16
    0.05
    2019
    +0.16
    0.05
    Negative Logits
     satchel
    -0.62
    的状态
    -0.61
    近くに
    -0.61
    的关键
    -0.61
     Վեր
    -0.61
    ,
    -0.59
    的过程
    -0.58
    是这样的
    -0.58
    层面
    -0.58
     so
    -0.58
    POSITIVE LOGITS
     antik
    1.38
     magis
    1.36
     kafe
    1.30
     silikon
    1.29
     socie
    1.28
     pama
    1.27
     teras
    1.26
     seksi
    1.24
     alkoh
    1.22
     kask
    1.21
    Activations Density 0.184%

    No Known Activations