© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude in an email 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
    36
    +0.12
    0.4%
    484
    +0.10
    0.3%
    1379
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.03
    4
    +0.10
    0.03
    1601
    +0.09
    0.03
    Negative Logits
     resultList
    -0.75
     newArr
    -0.66
     updatedAt
    -0.65
     ecru
    -0.64
     apprehen
    -0.63
     unlaw
    -0.61
     quitted
    -0.61
     répon
    -0.61
     🤣🤣
    -0.59
     swarovski
    -0.57
    POSITIVE LOGITS
    <bos>
    0.64
    ostante
    0.50
     acept
    0.48
     aclar
    0.46
     Савезне
    0.46
     sko
    0.45
     skr
    0.45
     lune
    0.44
    鞍
    0.43
     toler
    0.43
    Activations Density 0.066%

    No Known Activations