© 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. 11117
    Prev
    Next
    INDEX
    Explanations

    keywords related to JSON, text content, and serialization

    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
    876
    +0.14
    0.4%
    1150
    +0.13
    0.4%
    222
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.14
    0.00
    1284
    +0.13
    0.02
    678
    +0.09
    0.03
    Negative Logits
     bakteri
    -0.74
     Irán
    -0.71
     Singapur
    -0.62
     kalori
    -0.61
     bakter
    -0.59
     kooper
    -0.58
    República
    -0.58
     Demokrat
    -0.57
    Cuar
    -0.56
    Biografía
    -0.56
    POSITIVE LOGITS
     increa
    1.29
     guarante
    1.27
     compen
    1.24
     ?...
    1.21
     effe
    1.21
     affor
    1.20
     encomp
    1.18
     impra
    1.17
     !...
    1.14
     strick
    1.13
    Activations Density 0.141%

    No Known Activations