© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3523
    Prev
    Next
    INDEX
    Explanations

    information related to technology updates and advancements

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    2034
    +0.14
    0.4%
    2019
    +0.11
    0.3%
    1177
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.14
    0.16
    1203
    +0.11
    0.15
    1200
    +0.10
    0.16
    Negative Logits
    Πηγή
    -0.90
    ביוגרפיה
    -0.90
    astéro
    -0.88
    Ngoài
    -0.86
    Aún
    -0.82
    Asimismo
    -0.82
    Quiénes
    -0.81
    Από
    -0.81
    Todavía
    -0.81
     AssemblyCompany
    -0.81
    POSITIVE LOGITS
     depic
    2.02
     affor
    1.99
     impra
    1.99
     maneu
    1.97
     unden
    1.95
     encomp
    1.93
     guarante
    1.88
     reluct
    1.88
     snoopy
    1.87
     increa
    1.86
    Activations Density 3.057%

    No Known Activations