© 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. 6793
    Prev
    Next
    INDEX
    Explanations

    variety of beverages and associated details

    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
    906
    +0.13
    0.5%
    1403
    +0.13
    0.5%
    1343
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.13
    0.00
    16
    +0.13
    0.04
    605
    +0.13
    0.01
    Negative Logits
    STRUCTIONS
    -0.72
    FORMANCE
    -0.64
    TRIBUTION
    -0.59
     tubercle
    -0.58
     különböz
    -0.55
     얼
    -0.55
    NECTION
    -0.54
    ."
    -0.54
     udrž
    -0.54
    NECTIONS
    -0.54
    POSITIVE LOGITS
     prétend
    1.05
     prouve
    1.02
     préc
    1.00
     rafra
    0.94
     rassemble
    0.94
     représ
    0.92
    Caratter
    0.92
     regroupe
    0.91
     ciasc
    0.90
     quoique
    0.89
    Activations Density 0.155%

    No Known Activations