© 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. 14783
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code related to styling and web design properties

    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
    453
    +0.16
    0.5%
    876
    +0.14
    0.4%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.16
    0.04
    876
    +0.14
    -0.00
    2008
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.12
     vainly
    -0.57
     about
    -0.57
     former
    -0.56
     endeavouring
    -0.55
     unjustly
    -0.55
     obstinate
    -0.53
     intrigu
    -0.53
     and
    -0.53
     vexed
    -0.53
    POSITIVE LOGITS
     soggior
    1.14
     ristor
    1.13
     affez
    1.10
     sappi
    1.08
     exé
    1.03
     tranquillo
    0.98
     scuro
    0.97
     germain
    0.97
     cioc
    0.96
     camicia
    0.96
    Activations Density 0.167%

    No Known Activations